← All benchmarks

Claude Opus 5 (Adaptive Reasoning, High Effort)

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

Intelligence Index
58.9
Output speed
59.1
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
14.56s

Model metadata

Model ID712be54a-77ae-41b2-9a58-21181479d6ee
Slugclaude-opus-5-high
Release date2026-07-24
ProviderAnthropic
Provider sluganthropic
Output speed59.1 tok/s
Time to first token14.56s
Time to first answer14.56s
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 index76.50
artificial analysis intelligence index58.90
artificial analysis math index
gpqa93.7%
hle50.7%
ifbench
lcr67.0%
livecodebench
math 500
mmlu pro
scicode54.3%
tau banking32.8%
tau2
terminalbench hard
terminalbench v2 187.6%

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

Benchmark data from Artificial Analysis.