SEA-HELM (English) - IFEval: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 91.69 |
| 2 | Llama 3.3 70B Instruct | 89.89 |
| 3 | Gemma 4 12B (IT) | 89.89 |
| 4 | Gemma 4 26B A4B (IT) | 89.66 |
| 5 | Qwen 3.5 27B | 87.9 |
| 6 | Qwen 3.5 122B A10B | 87.74 |
| 7 | Olmo 3.1 32B Instruct | 86.75 |
| 8 | Qwen 3 VL 8B Instruct | 85.46 |
| 9 | Qwen 3.6 27B | 84.93 |
| 10 | Qwen 3.5 35B A3B | 84.92 |
| 11 | Llama 4 Scout Instruct | 84.7 |
| 12 | gemma-4-E4B-it | 84.34 |
| 13 | Qwen 3 VL 32B Instruct | 83.09 |
| 14 | Qwen 3.6 35B A3B | 82.71 |
| 15 | Qwen 3 VL 4B Instruct | 82.6 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-english-ifeval · How It Works · Data refreshed daily, snapshot 2026-09-19.