HELM Arabic - Arabic Mmlu - Economics (Middle School): leaderboard
HELM Arabic (release v2.2.0) ArabicMMLU Economics (Middle School): native Arabic multiple-choice questions from ArabicMMLU, which draws on school, university and professional exams across Arabic-speaking countries; 87 questions, exact match. Percent correct, 0-100, higher is better.
Metric: Exact Match (%). Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 41 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 89.66 | #51 |
| 2 | GPT-5.1 (2025-11-13) | 87.36 | #107 |
| 3 | Gemini 2.5 Flash (Non-reasoning) | 87.36 | #255 (Gemini 2.5 Flash) |
| 4 | Qwen 3.5 397B A17B | 85.06 | #154 |
| 5 | Claude Sonnet 4.6 | 83.91 | #94 |
| 6 | GPT-4.1 (2025-04-14) | 83.91 | #257 |
| 7 | Gemma 4 31B (IT) | 82.76 | #178 |
| 8 | AceGPT-v2-32B-Chat | 82.76 | #518 |
| 9 | AceGPT-v2-70B-Chat | 82.76 | #421 |
| 10 | GPT-5.4 (2026-03-05) | 82.76 | #63 |
| 11 | GPT-5.4 Nano (2026-03-17) | 82.76 | #285 |
| 12 | GPT-4.1 Mini | 81.61 | #363 |
| 13 | Qwen 3 Next 80B A3B Instruct | 81.61 | #381 |
| 14 | Gemini 2.5 Flash Lite (Non-reasoning) | 81.61 | #432 (Gemini 2.5 Flash Lite) |
| 15 | GPT-5.4 Mini (2026-03-17) | 81.61 | #180 |
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-middle-school · How It Works · Data refreshed daily, snapshot 2026-11-05.