HELM Arabic - Aratrust: leaderboard
The "Aratrust" subtask of HELM Arabic. Stanford HELM's Arabic project: Modern Standard Arabic knowledge, reasoning and understanding scenarios (AlGhafa, Arabic MMLU, exams and native-authored sets) run through the HELM harness with exact-match style metrics.
Metric: EM. Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 41 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mistral Large 3 | 94.56 | #409 |
| 2 | Claude Opus 4.7 | 94.3 | #51 |
| 3 | GPT-5.1 (2025-11-13) | 94.11 | #106 |
| 4 | Gemini 2.5 Flash Lite (Non-reasoning) | 94.01 | #426 (Gemini 2.5 Flash Lite) |
| 5 | Llama 4 Maverick Instruct FP8 | 93.96 | #414 |
| 6 | Gemini 2.5 Flash (Non-reasoning) | 93.89 | #247 (Gemini 2.5 Flash) |
| 7 | DeepSeek V3.1 | 93.25 | #268 |
| 8 | Claude Haiku 4.5 (20251001) | 93.22 | #254 |
| 9 | GPT-4.1 (2025-04-14) | 93.13 | #252 |
| 10 | Gemma 4 31B (IT) | 93.1 | #179 |
| 11 | Qwen 3.5 397B A17B | 92.68 | #148 |
| 12 | Claude Sonnet 4.6 | 92.26 | #93 |
| 13 | GPT-5.4 Mini (2026-03-17) | 91.82 | #173 |
| 14 | Qwen 3 Next 80B A3B Instruct | 91.44 | #373 |
| 15 | GPT-5.4 (2026-03-05) | 91.39 | #58 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-arabic-aratrust · How It Works · Data refreshed daily, snapshot 2026-10-24.