LiveBench · If
The Frontier
Best score over time · one chart, every benchmark
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with LiveBench · If
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Full rankings
29 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  GLM 5.1 | 68.5 |
| 2 |  Gemma 4 31B | 67.6 |
| 3 |  GPT-5.1-Codex-Max | 67.1 |
| 4 | GPT-5.2-Codex | 66.5 |
| 5 | GPT-5 Mini | 64.2 |
| 6 | GPT-5.1-Codex | 63.4 |
| 7 |  Kimi K2 Thinking | 62.0 |
| 8 |  MiniMax M2.7 | 61.1 |
| 9 | GPT-5.1-Codex-Mini | 59.0 |
| 10 |  Qwen3.6 Plus | 58.3 |
| 11 | MiniMax M2.5 | 57.2 |
| 12 | GLM 5 | 55.3 |
| 13 | GPT-5 Nano | 52.0 |
| 14 | gpt-oss-120b | 50.3 |
| 15 |  MiMo-V2-Pro | 43.2 |
| 16 | Qwen3 Next 80B A3B Thinking | 41.5 |
| 17 | Qwen3 235B A22B Thinking 2507 | 40.6 |
| 18 | GLM 4.7 | 35.7 |
| 19 |  Nemotron 3 Super | 28.4 |
| 20 | GLM 5V Turbo | 27.2 |
| 21 | GLM 4.6 | 26.2 |
| 22 |  DeepSeek V3.2 | 23.1 |
| 23 | Qwen3 235B A22B Instruct 2507 | 21.7 |
| 24 | DeepSeek V3.2 Exp | 19.3 |
| 25 | Qwen3 Next 80B A3B Instruct | 19.2 |
| 26 | GPT-5.4 Mini | 18.9 |
| 27 | GLM 4.6V | 17.1 |
| 28 | GPT-5.4 Nano | 16.5 |
| 29 |  Devstral 2 2512 | 13.5 |
Frequently asked
Pulled from the LiveBench · If dataset · updated daily
What does LiveBench · If measure?
LiveBench · If is a knowledge benchmark in the BenchGecko catalog. 29 AI models have been tested on it. Scores range from 13.5 to 68.5 out of 100.
Which model leads on LiveBench · If?
GLM 5.1 from z-ai leads LiveBench · If with a score of 68.5. The median score across 29 tested models is 43.2.
Is LiveBench · If saturated?
No · the top score is 68.5 out of 100 (68%). There is still meaningful room for improvement on LiveBench · If.
Does LiveBench · If predict performance on other benchmarks?
Yes · LiveBench · If scores correlate 0.83 with LiveBench · Overall across 29 shared models. Models that do well on LiveBench · If tend to do well on LiveBench · Overall.
How often is LiveBench · If data refreshed?
BenchGecko pulls updates daily. New model scores on LiveBench · If appear as soon as they are published by Epoch AI or the model provider.
More knowledge benchmarks
Same category · related evaluations