OpenCompass · IFEval
The Frontier
Best score over time · one chart, every benchmark
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with OpenCompass · IFEval
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Full rankings
32 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  Kimi K2.5 | 93.9 |
| 2 |  GLM 5 | 93.2 |
| 3 |  Step 3.5 Flash | 93.2 |
| 4 | Kimi K2 Thinking | 92.4 |
| 5 |  DeepSeek V3.2 Speciale | 91.7 |
| 6 |  Qwen3.5 397B A17B | 91.5 |
| 7 |  MiniMax M2.5 | 91.1 |
| 8 | GLM 4.7 | 90.2 |
| 9 |  gpt-oss-120b (free) | 90.2 |
| 10 |  LongCat Flash Chat | 90.2 |
| 11 | MiniMax M2 | 90.2 |
| 12 |  Gemini 2.5 Pro | 90.0 |
| 13 | DeepSeek V3.2 | 89.7 |
| 14 | Qwen3 30B A3B Thinking 2507 | 89.7 |
| 15 |  MiMo-V2-Flash | 89.5 |
| 16 | Qwen3 Next 80B A3B Thinking | 89.5 |
| 17 | gpt-oss-20b (free) | 88.9 |
| 18 | GLM 4.6 | 88.7 |
| 19 | Qwen3 4B Thinking 2507 | 88.5 |
| 20 |  Claude Sonnet 4 | 88.3 |
| 21 | Qwen3 235B A22B Instruct 2507 | 88.3 |
| 22 | Qwen3 235B A22B Thinking 2507 | 87.8 |
| 23 | Qwen3 Next 80B A3B Instruct | 87.6 |
| 24 | Qwen3 32B | 86.0 |
| 25 | Qwen3 8B | 85.6 |
| 26 | GLM 4.5 | 85.4 |
| 27 | Qwen3 30B A3B Instruct 2507 | 83.9 |
| 28 | Qwen3 4B Instruct 2507 | 82.4 |
| 29 |  ERNIE 4.5 21B A3B Thinking | 81.2 |
| 30 | Gemma 3 27B | 81.0 |
| 31 | R1 0528 | 80.0 |
| 32 |  Hunyuan A13B Instruct | 60.3 |
Frequently asked
Pulled from the OpenCompass · IFEval dataset · updated daily
What does OpenCompass · IFEval measure?
OpenCompass · IFEval is a knowledge benchmark in the BenchGecko catalog. 32 AI models have been tested on it. Scores range from 60.3 to 93.9 out of 100.
Which model leads on OpenCompass · IFEval?
Kimi K2.5 from moonshotai leads OpenCompass · IFEval with a score of 93.9. The median score across 32 tested models is 89.2.
Is OpenCompass · IFEval saturated?
No · the top score is 93.9 out of 100 (94%). There is still meaningful room for improvement on OpenCompass · IFEval.
Does OpenCompass · IFEval predict performance on other benchmarks?
Yes · OpenCompass · IFEval scores correlate 0.90 with LiveBench · Overall across 10 shared models. Models that do well on OpenCompass · IFEval tend to do well on LiveBench · Overall.
How often is OpenCompass · IFEval data refreshed?
BenchGecko pulls updates daily. New model scores on OpenCompass · IFEval appear as soon as they are published by Epoch AI or the model provider.
Top on OpenCompass · IFEval
Kimi K2.5 · 93.9GLM 5 · 93.2Step 3.5 Flash · 93.2Kimi K2 Thinking · 92.4DeepSeek V3.2 Speciale · 91.7More knowledge benchmarks
Same category · related evaluations