Benchmark
CursorBench 3.2
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 70.3%
- Mean
- 70.5%
- Median
- 2.2%
- Std dev
- 67.2%
- 10th percentile
- 73.4%
- 90th percentile
- 67.2%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5.1Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.4% |
| 2 | Claude Fable 5Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.5% |
| 3 | Claude Opus 5Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70% |
| 4 | GPT-5.6 SolAnthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.2% |