← All benchmarks

Claude Opus 5 (Adaptive Reasoning, Medium Effort)

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

Intelligence Index
56.3
Output speed
59.3
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
9.83s

Model metadata

Model IDff51be8f-e362-4a7e-9043-687ba15de207
Slugclaude-opus-5-medium
Release date2026-07-24
ProviderAnthropic
Provider sluganthropic
Output speed59.3 tok/s
Time to first token9.83s
Time to first answer9.83s
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 index74.30
artificial analysis intelligence index56.30
artificial analysis math index
gpqa91.9%
hle49.2%
ifbench
lcr69.0%
livecodebench
math 500
mmlu pro
scicode50.7%
tau banking28.7%
tau2
terminalbench hard
terminalbench v2 186.1%

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

Benchmark data from Artificial Analysis.