An
claude-opus-4-6 Benchmark & Insights
Anthropic Claude API
Updated Jul 18, 2026 All models
Sample size
156 runs
in window
Accuracy
92.5%
consensus match · 160d
Confidence
89%
over 161 runs
Window end
Jul 18, 2026
most recent run
Input price
$5.00/MTok
prompt tokens
Output price
$25.00/MTok
completion tokens
Model insights
- 01 A hair behind opus-4-8 but with a perfect "safe" record — it never called a dangerous day "safe".
- 02 Its misses are almost all soft "low"-vs-"medium" underratings scattered evenly across the window, making it the steadier of the two Opus versions despite the lower headline number.
Recent forecasts