← All comparisons

Claude 3.5 Sonnet (Oct '24) vs Claude Opus 4.6 (Non-reasoning, High Effort)

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)Claude Opus 4.6 (Non-reasoning, High Effort)
Intelligence Index15.946.5
Coding Index30.247.6
Math Index
Output speed (tok/s)0.058.4
Blended price ($/1M)$6.56$10.94
Time to first token (s)0.00s1.20s
aime15.7%
aime 25
artificial analysis coding index30.2047.60
artificial analysis intelligence index15.9046.50
artificial analysis math index
gpqa59.9%84.0%
hle3.9%18.6%
ifbench44.6%
lcr58.3%
livecodebench38.1%
math 50077.1%
mmlu pro77.2%
scicode36.6%45.7%
tau284.8%
terminalbench hard48.5%

Benchmark data from Artificial Analysis.