LiveBench · Data Analysis
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 · Data Analysis
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Full rankings
29 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  GPT-5.2-Codex | 78.2 |
| 2 |  Qwen3.6 Plus | 69.9 |
| 3 |  GLM 5 | 67.9 |
| 4 | GLM 5.1 | 63.2 |
| 5 | GPT-5.1-Codex | 60.8 |
| 6 |  Gemma 4 31B | 58.8 |
| 7 |  MiniMax M2.7 | 56.3 |
| 8 | GLM 4.7 | 55.2 |
| 9 | GPT-5.1-Codex-Max | 54.9 |
| 10 | GLM 5V Turbo | 54.1 |
| 11 | Qwen3 Next 80B A3B Thinking | 53.6 |
| 12 |  Kimi K2 Thinking | 52.3 |
| 13 | Qwen3 235B A22B Thinking 2507 | 52.2 |
| 14 | GLM 4.6 | 52.0 |
| 15 | Qwen3 Next 80B A3B Instruct | 49.8 |
| 16 | GPT-5.1-Codex-Mini | 49.7 |
| 17 | GPT-5 Mini | 49.6 |
| 18 | MiniMax M2.5 | 49.6 |
| 19 |  MiMo-V2-Pro | 49.2 |
| 20 | GPT-5.4 Mini | 47.4 |
| 21 | GLM 4.6V | 46.4 |
| 22 |  DeepSeek V3.2 | 45.0 |
| 23 | Qwen3 235B A22B Instruct 2507 | 44.7 |
| 24 | GPT-5 Nano | 44.3 |
| 25 | DeepSeek V3.2 Exp | 44.3 |
| 26 | GPT-5.4 Nano | 39.1 |
| 27 |  Devstral 2 2512 | 39.1 |
| 28 | gpt-oss-120b | 38.8 |
| 29 |  Nemotron 3 Super | 21.2 |
Frequently asked
Pulled from the LiveBench · Data Analysis dataset · updated daily
What does LiveBench · Data Analysis measure?
LiveBench · Data Analysis is a knowledge benchmark in the BenchGecko catalog. 29 AI models have been tested on it. Scores range from 21.2 to 78.2 out of 100.
Which model leads on LiveBench · Data Analysis?
GPT-5.2-Codex from OpenAI leads LiveBench · Data Analysis with a score of 78.2. The median score across 29 tested models is 49.8.
Is LiveBench · Data Analysis saturated?
No · the top score is 78.2 out of 100 (78%). There is still meaningful room for improvement on LiveBench · Data Analysis.
Does LiveBench · Data Analysis predict performance on other benchmarks?
Yes · LiveBench · Data Analysis scores correlate 0.84 with LiveBench · Overall across 29 shared models. Models that do well on LiveBench · Data Analysis tend to do well on LiveBench · Overall.
How often is LiveBench · Data Analysis data refreshed?
BenchGecko pulls updates daily. New model scores on LiveBench · Data Analysis appear as soon as they are published by Epoch AI or the model provider.
Top on LiveBench · Data Analysis
GPT-5.2-Codex · 78.2Qwen3.6 Plus · 69.9GLM 5 · 67.9GLM 5.1 · 63.2GPT-5.1-Codex · 60.8More knowledge benchmarks
Same category · related evaluations