Instruction following
IFBench
Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better.
Rankings
Higher is betterIFBench — frequently asked questions
- What is IFBench?
- Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better.
- Which AI model scores highest on IFBench?
- Qwen3.8-27B by Qwen holds the best IFBench result among tracked models, at 79.5% (released Aug 14 2026). Higher scores are better on this benchmark.
- What are the top 1 models on IFBench?
- 1. Qwen3.8-27B (Qwen) — 79.5%.
- How many models have a published IFBench score?
- 1 tracked model has a published IFBench score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.
- What is the best open model on IFBench?
- Qwen3.8-27B by Qwen is the highest-ranked model with downloadable weights on IFBench, scoring 79.5% at rank 1 overall.