IFBench: leaderboard
Instruction-following benchmark evaluating a model's ability to follow complex instructions.
Metric: Score (%). Source: arxiv.org. Source: benchmarklist.com. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nemotron 3.5 Lightning | 71.67 | #467 |
| 2 | Qwen 3.6 35B A3B | 64.21 | #226 |
| 3 | Gemma 4 26B A4B | 47.44 | #358 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ifbench · How It Works · Data refreshed daily, snapshot 2026-10-20.