An
claude-sonnet-5 Benchmark & Insights
Anthropic Claude API
Updated Jul 18, 2026 All models
Sample size
156 runs
in window
Accuracy
87.5%
consensus match · 160d
Confidence
85%
over 162 runs
Window end
Jul 18, 2026
most recent run
Input price
$2.00/MTok
prompt tokens
Output price
$10.00/MTok
completion tokens
Model insights
- 01 Every single miss is an underrating (21 under, 0 over) — it is the most consistently "optimistic" Claude, repeatedly saying "low" on "medium" days and calling "safe" on the "unsafe" 2026-02-18, 02-25 and 07-05.
- 02 Intro-priced at $2/$10 it still loses to claude-haiku-4-5 at half the cost.
Notes
Introductory pricing of $2/$10 per million input/output tokens is in effect through August 31, 2026, after which the standard pricing of $3/$15 per million input/output tokens will take effect.
Recent forecasts