← All benchmarks

Claude Opus 4.5 (Reasoning)

Anthropic · Released 2025-11-24 · Independent benchmark scores from Artificial Analysis

Intelligence Index
40.8
Output speed
0.0
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
0.00s

Model metadata

Model ID2660d74f-ce79-48a8-8b53-6e668e2071a2
Slugclaude-opus-4-5-thinking
Release date2025-11-24
ProviderAnthropic
Provider sluganthropic
Output speed0.0 tok/s
Time to first token0.00s
Time to first answer0.00s
Blended price ($/1M)$10.00
Input price ($/1M)$5.00
Output price ($/1M)$25.00

All evaluation scores (17)

aime
aime 2591.3%
artificial analysis coding index
artificial analysis intelligence index40.80
artificial analysis math index91.30
gpqa86.6%
hle28.4%
ifbench58.0%
lcr74.0%
livecodebench87.1%
math 500
mmlu pro89.5%
scicode49.5%
tau banking
tau289.5%
terminalbench hard47.0%
terminalbench v2 1

Source: artificialanalysis.ai/models/claude-opus-4-5-thinking

Benchmark data from Artificial Analysis.