Benchmark
FrontierBench v0.1
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models measured
- 4
- Scores recorded
- 6
- Sources
- 2
- IQ weight
- No weight published
Score distribution
- 36.7%
- Mean
- 43.3%
- Median
- 8.2%
- Std dev
- 33.8%
- 10th percentile
- 44.4%
- 90th percentile
- 21.1%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5Anthropic self-run · xhigh· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.4% |
| 2 | Claude Opus 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.3% |
| 3 | Claude Opus 5Harbor-reported· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 43.3% |
| 4 | GPT-5.6 SolCodex· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 34.4% |
| 5 | Claude Fable 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33.8% |
| 6 | Claude Opus 4.8Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 21.1% |
Data credits: 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. · Data by LLM Stats