← All benchmarks

Claude Opus 5 (Adaptive Reasoning, Max Effort)

Anthropic · Released 2026-07-24 · Independent benchmark scores from Artificial Analysis

Intelligence Index
60.7
Output speed
62.8
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
31.35s

Model metadata

Model IDb8fc61f7-5e9a-49e6-8547-6ac56db24627
Slugclaude-opus-5
Release date2026-07-24
ProviderAnthropic
Provider sluganthropic
Output speed62.8 tok/s
Time to first token31.35s
Time to first answer31.35s
Blended price ($/1M)$10.00
Input price ($/1M)$5.00
Output price ($/1M)$25.00

All evaluation scores (17)

aime
aime 25
artificial analysis coding index78.00
artificial analysis intelligence index60.70
artificial analysis math index
gpqa93.2%
hle52.6%
ifbench
lcr70.0%
livecodebench
math 500
mmlu pro
scicode55.7%
tau banking30.3%
tau2
terminalbench hard
terminalbench v2 189.1%

Source: artificialanalysis.ai/models/claude-opus-5

Benchmark data from Artificial Analysis.