HELM AFR - MMLU College Medicine (Northern Sotho): leaderboard
Metric: EM. Source: crfm.stanford.edu. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 74.57 |
| 2 | Claude 3.7 Sonnet (20250219) | 67.63 |
| 3 | Gemini 2.0 Flash Lite | 65.32 |
| 4 | GPT-4o (2024-08-06) | 58.96 |
| 5 | DeepSeek V3 | 58.38 |
| 6 | Llama 3.1 405B Instruct | 54.34 |
| 7 | Llama 3.1 70B Instruct | 52.6 |
| 8 | Llama 3.3 70B Instruct | 50.29 |
| 9 | GPT-4 Turbo | 43.93 |
| 10 | Gemma 2 27B (IT) | 43.35 |
| 11 | GPT-3.5 Turbo (0125) | 40.46 |
| 12 | Qwen 2.5 72B Instruct | 38.73 |
| 13 | Llama 3.1 8B Instruct | 34.68 |
| 14 | Claude 3.5 Haiku (20241022) | 34.68 |
| 15 | Gemma 2 9B (IT) | 32.37 |
Interactive version: theaggregate.ai/benchmark?slug=helm-afr-mmlu-college-medicine-northern-sotho · How It Works · Data refreshed daily, snapshot 2026-09-08.