Benchmark
BioMysteryBench
Scores are percentages. Higher is better.
- Models measured
- 12
- Scores recorded
- 30
- Sources
- 2
- IQ weight
- 0.00
Score distribution
- 66.1%
- Mean
- 71.3%
- Median
- 21.3%
- Std dev
- 40%
- 10th percentile
- 89.3%
- 90th percentile
- 20.9%
- Min
This benchmark has a weight of 0.00 for chat models, measured over 12 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 Opus 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Solvable · 73 tasks· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 91.4% |
| 2 | Claude Opus 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.1% |
| 3 | Claude Opus 5Anthropic Opus 5 launch table · adaptive thinking · max effort unless noted · human-solvable subset· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.1% |
| 4 | Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.3% |
| 5 | Claude Opus 5.5Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Solvable · 73 tasks· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.3% |
| 6 | Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.2% |
| 7 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Human Solvable subset· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.2% |
| 8 | Gemini 3.8 FlashHuman Solvable subset· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.8% |
| 9 | Gemini 3.7 FlashHuman Solvable subset· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 87.1% |
| 10 | Claude Sonnet 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Solvable · 73 tasks· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.9% |
| 11 | Claude Sonnet 5human-solvable subset · source plots 0.82· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82% |
| 12 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.6% |
| 13 | Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · Human· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 80.4% |
| 14 | Claude Opus 4.7Verified subset · bash/package tools · thinking disabled· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 78.9% |
| 15 | Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.3% |
| 16 | Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.3% |
| 17 | Gemini 3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 56.5% |
| 18 | Gemini 3.8 FlashHuman Difficult subset· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.5% |
| 19 | Claude Opus 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Difficult · 17 tasks· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.8% |
| 20 | Claude Sonnet 4.6bash/code/package tools · no extended thinking· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.4% |
| 21 | Claude Opus 5.5Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Difficult · 17 tasks· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50% |
| 22 | Claude Opus 5Anthropic Opus 5 launch table · adaptive thinking · max effort unless noted · hard subset· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.4% |
| 23 | Claude Fable 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.1% |
| 24 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Human Difficult subset· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.7% |
| 25 | Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.5% |
| 26 | Gemini 3.7 FlashHuman Difficult subset· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 43.5% |
| 27 | Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · Hard· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 40% |
| 28 | Claude Sonnet 5Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Difficult · 17 tasks· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 39.4% |
| 29 | Claude Sonnet 5human-difficult subset · source plots 0.35· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 35% |
| 30 | Claude Opus 4.7Hard subset · objective ground truth · unsolved by human experts · bash/package tools · thinking disabled· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 20.9% |
Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.