Agnes-SeaLLM-8B
Introduction
We introduce Agnes-SeaLLM-8B, a compact Large Language Model (LLM) meticulously optimized for Southeast Asian languages. Despite its efficient footprint, it delivers performance rivaling much larger open-source models, excelling in tasks such as mathematical reasoning, translation, and instruction following. Furthermore, it has been specially tuned to enhance reliability, minimize hallucinations, and provide culturally sensitive, safe responses tailored to the Southeast Asian context.

🔥 Highlights
Compact Efficiency & Rapid Deployment: Significantly smaller than mainstream LLMs, Agnes-SeaLLM-8B enables high-speed inference and low-resource deployment without sacrificing accuracy or multilingual proficiency. It is the ideal choice for edge devices and resource-constrained environments.
Top-Tier Performance in its Class: Outperforms comparable open-source models across multi-dimensional benchmarks, including academic examinations, complex instruction following, mathematics, and high-precision translation.
Superior Instruction Following: Demonstrates exceptional capability in handling multi-turn dialogues and executing complex, nuanced tasks with high fidelity.
Safe, Reliable, and Culturally Aware: Engineered to reduce hallucinations and increase sensitivity to Southeast Asian cultural nuances. This ensures safer interactions while maintaining peak performance in English and Chinese.
Balanced Multilingual Mastery: Maintains high-quality, consistent output across a broad linguistic spectrum, overcoming the "seesaw effect" often found in regional models.
【SeaExam Summary statistics】
<div id="m3exam-summary" style="width: 100%; max-height: 420px; overflow: auto; border: 1px solid #ddd; border-radius: 6px; margin-bottom: 20px;">
<table width="100%" style="border-collapse: collapse; width: 100% !important; min-width: 100% !important; table-layout: fixed; font-family: sans-serif; font-size: 14px; display: table !important;">
<colgroup>
<col style="width: 40%;" />
<col style="width: 20%;" />
<col style="width: 20%;" />
<col style="width: 20%;" />
</colgroup>
<thead>
<tr>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: left; border-bottom: 2px solid #ddd; padding: 12px 8px; white-space: nowrap; z-index: 10;">Model</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10;">avg</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10;">M3Exam</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10;">MMLU</th>
</tr>
</thead>
<tbody>
<tr style="background-color: #f9f9f9;">
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap; overflow: hidden; text-overflow: ellipsis;">Agnes-SeaLLM-8B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>75.32</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>77.47</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>74.13</strong></td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Llama-sea-Lion-v2-8B-IT</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">55.86</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">61.11</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">52.91</td>
</tr>
<tr> <td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Sailor2-20B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">67.50</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">74.15</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.77</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">glm-4-9b-chat</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">64.35</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">69.36</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">61.53</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Meta-Llama-3-70B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.67</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">64.25</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.55</td>
</tr>
</tbody>
</table>
</div>
- Agnes-SeaLLM-8B (75.32 avg) crushes 8B peers and outpaces Sailor2-20B, offering 70B-tier performance with compact, low-resource deployment.
- Exceptional scores in both M3Exam and MMLU prove it bridges regional linguistic nuance with elite global reasoning.
【M3Exam Model evaluation sub-statistics】
<div id="m3exam-stats" style="width: 100%; max-height: 480px; overflow: auto; border: 1px solid #ddd; border-radius: 6px;">
<table style="border-collapse: collapse; width: 100%; table-layout: fixed; font-family: sans-serif; font-size: 14px;">
<thead>
<tr>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: left; border-bottom: 2px solid #ddd; padding: 12px 8px; white-space: nowrap; z-index: 10; width: 25%;">Model</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 12.5%;">avg</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 12.5%;">M3Exam<br />zh</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 12.5%;">M3Exam<br />en</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 12.5%;">M3Exam<br />id</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 12.5%;">M3Exam<br />vi</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 12.5%;">M3Exam<br />th</th>
</tr>
</thead>
<tbody>
<tr style="background-color: #f9f9f9;">
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap; overflow: hidden; text-overflow: ellipsis;">Agnes-SeaLLM-8B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>76.84</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">83.70</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>93.24</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>72.97</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>70.03</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">64.25</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Llama-sea-Lion-v2-8B-IT</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">59.95</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">52.95</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">78.41</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">54.37</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">54.00</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">60.00</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Sailor2-20B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">74.96</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">80.90</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">88.94</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">69.68</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">68.65</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>66.65</strong></td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">glm-4-9b-chat</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">71.62</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>85.71</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">89.78</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.16</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">66.02</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">53.43</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Meta-Llama-3-70B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.82</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.04</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">84.75</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">57.97</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">52.02</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">61.32</td>
</tr>
</tbody>
</table>
</div>
- With a 71.29 average, Agnes-SeaLLM-8B delivers "70B-class" performance in an 8B footprint, outperforming the 20B Sailor2 and crushing 8B peers like Llama-3 and GLM-4.
- It sets a new benchmark for Southeast Asia, achieving top-tier scores in Indonesian (72.97) and Vietnamese (70.03)**, while maintaining elite English (93.24) and Chinese (83.70) proficiency.
【MMLU Model evaluation sub-statistics】
<div id="mmlu-stats" style="width: 100%; max-height: 480px; overflow: auto; border: 1px solid #ddd; border-radius: 6px; margin-bottom: 20px;">
<table style="border-collapse: collapse; width: 100%; table-layout: fixed; font-family: sans-serif; font-size: 14px;">
<thead>
<tr>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: left; border-bottom: 2px solid #ddd; padding: 12px 8px; white-space: nowrap; z-index: 10; width: 22%;">Model</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 13%;">avg</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 13%;">MMLU<br />zh</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 13%;">MMLU<br />en</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 13%;">MMLU<br />id</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 13%;">MMLU<br />vi</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 12px 8px; z-index: 10; width: 13%;">MMLU<br />th</th>
</tr>
</thead>
<tbody>
<tr style="background-color: #f9f9f9;">
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap; overflow: hidden; text-overflow: ellipsis;">Agnes-SeaLLM-8B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>71.29</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>71.40</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>78.60</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>71.54</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>66.84</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>62.70</strong></td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Llama-sea-Lion-v2-8B-IT</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">55.86</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">49.58</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">61.65</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">54.42</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">47.72</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">51.19</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Sailor2-20B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">67.50</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">64.84</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">72.88</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">64.60</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">59.58</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">56.95</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">glm-4-9b-chat</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.35</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">64.84</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">72.42</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">60.04</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">60.04</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">50.32</td>
</tr>
<tr>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap;">Meta-Llama-3-70B</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">58.21</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">63.35</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">60.91</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">72.32</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">62.95</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">62.35</td>
</tr>
</tbody>
</table>
</div>
【Indonesian Fine-grained discipline statistics】
<div id="indonesian-benchmarks" style="width: 100%; max-height: 600px; overflow: auto; border: 1px solid #ddd;">
<table style="border-collapse: collapse; width: 100%; table-layout: auto; font-size: 13px;">
<thead>
<tr>
<th style="position: sticky; top: 0; left: 0; z-index: 2; background: #f7f7f7; text-align: left; border-bottom: 2px solid #ddd; padding: 10px 8px; white-space: nowrap;">Indonesian Standards</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 10px 8px; white-space: nowrap; font-weight: bold; color: #000;">Agnes-SeaLLM-8B</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 10px 8px; white-space: nowrap;">Sailor2-20B</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 10px 8px; white-space: nowrap;">glm-4-9b-chat</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 10px 8px; white-space: nowrap;">Llama-sea-Lion-v2-8B</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 2px solid #ddd; padding: 10px 8px; white-space: nowrap;">Meta-Llama-3-8B</th>
</tr>
</thead>
<tbody>
<tr style="background-color: #fff9f9;">
<td style="position: sticky; left: 0; background: #fff9f9; border-bottom: 1px solid #eee; padding: 10px 8px; white-space: nowrap; font-weight: bold;">Overall Average</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;"><strong>73.37</strong></td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">64.60</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">60.04</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">54.42</td>
<td style="border-bottom: 1px solid #eee; padding: 10px 8px; text-align: right;">54.60</td>
</tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">abstract_algebra</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>64.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">48.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">34.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">28.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">32.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">anatomy</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>70.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">62.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">46.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">46.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">50.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">astronomy</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>90.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">64.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">66.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">58.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">business_ethics</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>68.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">60.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">56.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">64.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">56.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">clinical_knowledge</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>84.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">66.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">64.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">66.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">college_biology</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>98.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">84.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">60.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">62.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">college_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>70.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">38.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">50.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">40.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">42.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">college_computer_science</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>74.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">54.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">52.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">36.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">38.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">college_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>60.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">38.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">42.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">32.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">38.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">college_medicine</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>86.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">66.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">74.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">64.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">college_physics</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>82.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">60.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">38.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">44.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">computer_security</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">80.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>86.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">64.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">50.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">56.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">conceptual_physics</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>84.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">72.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">44.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">46.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">elementary_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>92.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">78.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">78.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">72.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">80.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">high_school_biology</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>90.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">84.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">80.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">70.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">74.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">high_school_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>94.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">50.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">62.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">54.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">50.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">high_school_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>86.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">44.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">64.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">44.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">54.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">international_law</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">80.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>84.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">78.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">74.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">marketing</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>90.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">82.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">70.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">78.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">sociology</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>80.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">68.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">66.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">70.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">64.00</td></tr>
<tr><td style="position: sticky; left: 0; background: #fff; border-bottom: 1px solid #eee; padding: 8px; white-space: nowrap;">world_religions</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">76.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;"><strong>84.00</strong></td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">76.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">66.00</td><td style="border-bottom: 1px solid #eee; padding: 8px; text-align: right;">76.00</td></tr>
</tbody>
</table>
</div>
【MMLU Fine-grained discipline statistics】
<style>
#mmlu-fine th:first-child,
#mmlu-fine td:first-child {
padding-right: calc(8px + 4ch) !important;
}
</style>
<div id="mmlu-fine" style="max-height: 520px; overflow: auto; border: 1px solid #ddd;">
<table style="border-collapse: collapse; width: max-content; min-width: 980px;">
<thead>
<tr>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: left; border-bottom: 1px solid #ddd; padding: 6px 8px; white-space: nowrap;">language / subject</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 1px solid #ddd; padding: 6px 8px; white-space: nowrap;">Correct</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 1px solid #ddd; padding: 6px 8px; white-space: nowrap;">Total</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 1px solid #ddd; padding: 6px 8px; white-space: nowrap;">Accuracy</th>
<th style="position: sticky; top: 0; background: #f7f7f7; text-align: right; border-bottom: 1px solid #ddd; padding: 6px 8px; white-space: nowrap;">Percentage</th>
</tr>
</thead>
<tbody>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">2176</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">2850</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">76.35%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">12.81%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → abstract_algebra</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">36</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">72.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → anatomy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">31</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">62.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → astronomy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → business_ethics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">36</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">72.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → clinical_knowledge</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → college_biology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → college_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">37</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">74.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → college_computer_science</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → college_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → college_medicine</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → college_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → computer_security</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">39</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">78.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → conceptual_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → econometrics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → electrical_engineering</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">36</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">72.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → elementary_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">48</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">96.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → formal_logic</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">31</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">62.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → global_facts</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">26</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">52.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_biology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_computer_science</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">47</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">94.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_european_history</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_geography</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_government_and_politics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_macroeconomics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_microeconomics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_psychology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">47</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">94.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_statistics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_us_history</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">36</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">72.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → high_school_world_history</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → human_aging</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">31</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">62.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → human_sexuality</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → international_law</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → jurisprudence</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">33</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">66.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → logical_fallacies</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">37</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">74.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → machine_learning</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">36</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">72.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → management</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → marketing</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">44</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">88.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → medical_genetics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → miscellaneous</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">35</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">70.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → moral_disputes</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → moral_scenarios</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → nutrition</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → philosophy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">25</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → prehistory</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">37</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">74.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → professional_accounting</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">32</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">64.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → professional_law</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">28</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">56.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → professional_medicine</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">39</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">78.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → professional_psychology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">39</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">78.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → public_relations</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → security_studies</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → sociology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">38</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">76.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → us_foreign_policy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → virology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">24</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">48.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">chinese → world_religions</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">36</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">72.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">2402</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">2850</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.28%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">12.81%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → abstract_algebra</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">38</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">76.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → anatomy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → astronomy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → business_ethics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">39</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">78.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → clinical_knowledge</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → college_biology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">49</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">98.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → college_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">35</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">70.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → college_computer_science</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → college_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → college_medicine</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">47</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">94.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → college_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → computer_security</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → conceptual_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">44</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">88.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → econometrics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">44</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">88.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → electrical_engineering</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">39</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">78.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → elementary_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">49</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">98.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → formal_logic</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">36</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">72.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → global_facts</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">26</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">52.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_biology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">47</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">94.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_computer_science</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">100.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_european_history</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_geography</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_government_and_politics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">48</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">96.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_macroeconomics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_microeconomics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">48</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">96.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_psychology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_statistics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_us_history</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → high_school_world_history</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → human_aging</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">38</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">76.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → human_sexuality</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → international_law</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → jurisprudence</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">44</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">88.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → logical_fallacies</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → machine_learning</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → management</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → marketing</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → medical_genetics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → miscellaneous</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → moral_disputes</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → moral_scenarios</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → nutrition</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">44</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">88.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → philosophy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → prehistory</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → professional_accounting</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">37</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">74.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → professional_law</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">32</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">64.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → professional_medicine</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → professional_psychology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → public_relations</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → security_studies</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">39</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">78.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → sociology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → us_foreign_policy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">44</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">88.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → virology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">30</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">60.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">english → world_religions</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">2091</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">2850</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">73.37%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">12.81%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → abstract_algebra</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">32</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">64.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → anatomy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">35</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">70.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → astronomy</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → business_ethics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">34</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">68.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → clinical_knowledge</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → college_biology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">49</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">98.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → college_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">35</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">70.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → college_computer_science</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">37</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">74.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → college_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">30</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">60.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → college_medicine</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">43</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">86.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → college_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">41</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">82.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → computer_security</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">40</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">80.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → conceptual_physics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → econometrics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">35</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">70.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → electrical_engineering</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">32</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">64.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → elementary_mathematics</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">46</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">92.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → formal_logic</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">31</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">62.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → global_facts</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">28</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">56.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → high_school_biology</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → high_school_chemistry</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">47</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">94.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → high_school_computer_science</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">45</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">90.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → high_school_european_history</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">31</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">62.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
<tr><td style="border-bottom: 1px solid #eee; padding: 6px 8px; white-space: nowrap;">indonesian → high_school_geography</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">42</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">50</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">84.00%</td><td style="border-bottom: 1px solid #eee; padding: 6px 8px; text-align: right;">0.22%</td></tr>
The model card is truncated. Read the rest on Hugging Face.