HELM Arabic - Arabic Mmlu - Economics (University): leaderboard
HELM Arabic (release v2.2.0) ArabicMMLU Economics (University): native Arabic multiple-choice questions from ArabicMMLU, which draws on school, university and professional exams across Arabic-speaking countries; 137 questions, exact match. Percent correct, 0-100, higher is better.
Metric: Exact Match (%). Source: crfm.stanford.edu. Saturation forecast: Around February 2027. 41 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 83.21 | #51 |
| 2 | Claude Sonnet 4.6 | 82.48 | #94 |
| 3 | GPT-5.4 (2026-03-05) | 82.48 | #63 |
| 4 | GPT-5.1 (2025-11-13) | 79.56 | #107 |
| 5 | Gemini 2.5 Flash (Non-reasoning) | 79.56 | #255 (Gemini 2.5 Flash) |
| 6 | Gemma 4 31B (IT) | 78.1 | #178 |
| 7 | GPT-4.1 (2025-04-14) | 78.1 | #257 |
| 8 | Qwen 3.5 397B A17B | 76.64 | #154 |
| 9 | Claude Haiku 4.5 (20251001) | 75.18 | #264 |
| 10 | Qwen 3 Next 80B A3B Instruct | 74.45 | #381 |
| 11 | Gemini 2.5 Flash Lite (Non-reasoning) | 70.8 | #432 (Gemini 2.5 Flash Lite) |
| 12 | GPT-4.1 Mini | 69.34 | #363 |
| 13 | Qwen 2.5 72B Instruct | 68.61 | #469 |
| 14 | DeepSeek V3.1 | 68.61 | #275 |
| 15 | AceGPT-v2-70B-Chat | 68.61 | #421 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-arabic-arabic-mmlu-economics-university · How It Works · Data refreshed daily, snapshot 2026-11-05.