Skip to content

Benchmark

FrontierCode v1

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

27%
Mean
38.8%
Median
11.9%
Std dev
15.1%
10th percentile
38.8%
90th percentile
15.1%
Min
15.1%38.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Sonnet 5Cognition production evaluation · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.38.8%
2Claude Sonnet 4.6Cognition production evaluation· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.15.1%

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.