LLM-JP · Overall
The Frontier
Best score over time · one chart, every benchmark
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with LLM-JP · Overall
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Full rankings
11 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  DeepSeek R1 Distill Qwen 14B | 56.8 |
| 2 |  Qwen2 VL 7B Instruct | 53.0 |
| 3 | Qwen2 7B Instruct | 51.7 |
| 4 |  Meta Llama 3 8B Instruct | 49.6 |
| 5 | Meta Llama 3 8B | 48.9 |
| 6 | DeepSeek R1 Distill Llama 8B | 41.4 |
| 7 |  Gemma 2 2b It | 40.5 |
| 8 | DeepSeek R1 Distill Qwen 7B | 39.3 |
| 9 | Llama 2 7b Chat Hf | 38.3 |
| 10 | Llama 2 7b Hf | 37.2 |
| 11 | HF SmolLM2 135M Instruct | 15.6 |
Frequently asked
Pulled from the LLM-JP · Overall dataset · updated daily
What does LLM-JP · Overall measure?
LLM-JP · Overall is a knowledge benchmark in the BenchGecko catalog. 11 AI models have been tested on it. Scores range from 15.6 to 56.8 out of 100.
Which model leads on LLM-JP · Overall?
DeepSeek R1 Distill Qwen 14B from DeepSeek leads LLM-JP · Overall with a score of 56.8. The median score across 11 tested models is 41.4.
Is LLM-JP · Overall saturated?
No · the top score is 56.8 out of 100 (57%). There is still meaningful room for improvement on LLM-JP · Overall.
Does LLM-JP · Overall predict performance on other benchmarks?
Yes · LLM-JP · Overall scores correlate 0.90 with JCommonsenseQA across 11 shared models. Models that do well on LLM-JP · Overall tend to do well on JCommonsenseQA.
How often is LLM-JP · Overall data refreshed?
BenchGecko pulls updates daily. New model scores on LLM-JP · Overall appear as soon as they are published by Epoch AI or the model provider.
More knowledge benchmarks
Same category · related evaluations