HELM AFR - Overall (Afrikaans): leaderboard
Metric: Mean score. Source: crfm.stanford.edu. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-08-06) | 76.68 |
| 2 | DeepSeek V3 | 76.38 |
| 3 | Claude 3.7 Sonnet (20250219) | 76.03 |
| 4 | Gemini 2.0 Flash | 75.75 |
| 5 | Qwen 2.5 72B Instruct | 72.7 |
| 6 | Llama 3.1 70B Instruct | 70.41 |
| 7 | Gemini 2.0 Flash Lite | 69.73 |
| 8 | Gemma 2 27B (IT) | 63.63 |
| 9 | Claude 3.5 Haiku (20241022) | 63.39 |
| 10 | GPT-4 Turbo | 62.35 |
| 11 | GPT-3.5 Turbo (0125) | 58.19 |
| 12 | Llama 3.1 405B Instruct | 58.04 |
| 13 | Gemma 2 9B (IT) | 52.7 |
| 14 | Llama 3.3 70B Instruct | 52.24 |
| 15 | GPT-4o Mini (2024-07-18) | 48.67 |
Interactive version: theaggregate.ai/benchmark?slug=helm-afr-overall-afrikaans · How It Works · Data refreshed daily, snapshot 2026-09-08.