IFEval Leaderboard — leaderboard
Instruction Following Evaluation: tests LLMs on strict instruction adherence across prompt-level and instruction-level constraints using 25+ verifiable instruction types.
Metric: Final Score. Source: huggingface.co. Status: saturation imminent. 27 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3 70B | 83.31 |
| 2 | Qwen 2 72B | 80.56 |
| 3 | Llama 3 8B | 78.84 |
| 4 | Command-R+ | 77.01 |
| 5 | Mixtral 8x22B | 73.08 |
| 6 | Command R | 69.71 |
| 7 | Mistral-7B-v0.1 | 60.96 |
| 8 | Codestral-22B-v0.1 | 60.74 |
| 9 | Mixtral 8x7B (v0.1) | 60.12 |
| 10 | Mistral-7B-v0.3 | 56.89 |
Interactive version: theaggregate.ai/benchmark?slug=ifeval-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.