HELM AFR - MMLU College Medicine (Igbo): leaderboard
Metric: EM. Source: crfm.stanford.edu. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 69.36 |
| 2 | Claude 3.7 Sonnet (20250219) | 61.27 |
| 3 | DeepSeek V3 | 60.69 |
| 4 | Gemini 2.0 Flash Lite | 60.12 |
| 5 | GPT-4o (2024-08-06) | 58.96 |
| 6 | Llama 3.1 70B Instruct | 52.6 |
| 7 | Llama 3.1 405B Instruct | 51.45 |
| 8 | Llama 3.3 70B Instruct | 49.71 |
| 9 | GPT-4 Turbo | 47.98 |
| 10 | Gemma 2 27B (IT) | 40.46 |
| 11 | Qwen 2.5 72B Instruct | 38.73 |
| 12 | Llama 3.1 8B Instruct | 38.15 |
| 13 | Claude 3.5 Haiku (20241022) | 36.42 |
| 14 | GPT-3.5 Turbo (0125) | 33.53 |
| 15 | Gemma 2 9B (IT) | 30.06 |
Interactive version: theaggregate.ai/benchmark?slug=helm-afr-mmlu-college-medicine-igbo · How It Works · Data refreshed daily, snapshot 2026-09-08.