Benchmark
$OneMillion-Bench · Expert Score
Higher scores are better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- 0.44
Score distribution
- 49.7
- Mean
- 52.5
- Median
- 5.5
- Std dev
- 41.8
- 10th percentile
- 55.9
- 90th percentile
- 41.8
- Min
This benchmark has a weight of 0.44 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5Qwen表:expert score · Gemini 3.1 Pro Preview judge· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.9 |
| 2 | GPT-5.6 SolQwen表:expert score · Gemini 3.1 Pro Preview judge· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53.8 |
| 3 | Qwen3.8 MaxQwen表:expert score · Gemini 3.1 Pro Preview judge· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.5 |
| 4 | Qwen3.7 MaxQwen表:expert score · Gemini 3.1 Pro Preview judge· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.4 |
| 5 | Claude Opus 4.8Qwen表:expert score · Gemini 3.1 Pro Preview judge· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 41.8 |