TMMLU+ - Other: leaderboard
The "Other" category of TMMLU+, the Traditional Chinese multi-subject exam benchmark (ikala): 66 subjects drawn from Taiwanese professional, high-school and university examinations, answered as multiple choice and reported per category as well as overall.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around February 2027. 21 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 95.25 | #16 |
| 2 | GPT-5.6 Sol | 86.39 | #22 |
| 3 | Claude Fable 5 | 84.22 | #20 |
| 4 | DeepSeek V4 Pro (0813) | 83.92 | #58 |
| 5 | Claude Sonnet 5 | 81.9 | #65 |
| 6 | Gemini 3.1 Pro (Preview) (Thinking) | 81.76 | #64 (Gemini 3.1 Pro (Preview)) |
| 7 | Hy3 | 80.5 | #100 |
| 8 | DeepSeek V4 Flash | 80.42 | #155 |
| 9 | GPT-5.6 Terra | 80.07 | #40 |
| 10 | Qwen 3.8 27B | 79.61 | #123 |
| 11 | Kimi K3 | 78.03 | #35 |
| 12 | Qwen 3.7 Max | 77.25 | #85 |
| 13 | GPT-5.6 Luna | 76.48 | #79 |
| 14 | GLM-5.2 | 75.42 | #80 |
| 15 | Grok 4.3 | 74.79 | #204 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=tmmlu-plus-other · How It Works · Data refreshed daily, snapshot 2026-11-05.