← All benchmarks

Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

Anthropic · Released 2026-05-28 · Independent benchmark scores from Artificial Analysis

Intelligence Index
55.7
Output speed
66.8
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
35.19s

Model metadata

Model ID992b7b84-5069-4c6a-9295-834252553d50
Slugclaude-opus-4-8
Release date2026-05-28
ProviderAnthropic
Provider sluganthropic
Output speed66.8 tok/s
Time to first token35.19s
Time to first answer35.19s
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 index55.70
artificial analysis math index
gpqa92.0%
hle45.7%
ifbench62.2%
lcr67.7%
livecodebench
math 500
mmlu pro
scicode53.5%
tau banking27.6%
tau294.4%
terminalbench hard58.3%
terminalbench v2 184.6%

Source: artificialanalysis.ai/models/claude-opus-4-8

Benchmark data from Artificial Analysis.