An
claude-opus-5 Benchmark & Insights
Anthropic Claude Api
Updated Jul 31, 2026 All models
Sample size
168 runs
in window
Accuracy
93.5%
consensus match · 168d
Confidence
84%
over 168 runs
Window end
Jul 31, 2026
most recent run
Input price
$5.00/MTok
prompt tokens
Output price
$25.00/MTok
completion tokens
Model insights
- 01 The newest Anthropic flagship lands below the older Opus 4.8 at the same price.
- 02 Nearly every miss is downward, including five days it called "safe" against an "unsafe" consensus, plus a three-day mid-July streak of "low" on "medium" days.
Recent forecasts