HELM Arabic - Arabic Exams - Biology: leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 41 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 Mini | 45.71 |
| 2 | Llama 3.3 70B Instruct | 45.71 |
| 3 | Qwen 3 Next 80B A3B Instruct | 45.71 |
| 4 | Claude Sonnet 4.6 | 42.86 |
| 5 | GPT-5.4 (2026-03-05) | 42.86 |
| 6 | Gemma 4 31B (IT) | 40 |
| 7 | Claude Opus 4.7 | 40 |
| 8 | Qwen 3.5 397B A17B | 40 |
| 9 | Gemini 2.5 Flash (Thinking) | 40 |
| 10 | jais-adapted-13B-chat | 40 |
| 11 | Falcon3-10B-Instruct | 40 |
| 12 | GPT-4.1 Nano | 37.14 |
| 13 | Llama 4 Scout Instruct | 37.14 |
| 14 | GPT-4.1 (2025-04-14) | 37.14 |
| 15 | Qwen 3.5 9B | 37.14 |
Interactive version: theaggregate.ai/benchmark?slug=helm-arabic-arabic-exams-biology · How It Works · Data refreshed daily, snapshot 2026-09-19.