IFBench - release-reported instruction following
General QA
Verifiable instruction-following accuracy from a model release. Shares the IFBench group without claiming the evaluator-specific Artificial Analysis harness or item count.
Top models (higher is better)
| Model | Score |
|---|---|
| Qwen3.8-Flash-Next | 81.3 |
| Beam 1.0 501B A23B | 79.6 |