← All comparisons

Claude 3.5 Sonnet (Oct '24) vs Claude Opus 4.6 (Adaptive Reasoning, Max Effort)

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Intelligence Index15.952.9
Coding Index30.248.1
Math Index
Output speed (tok/s)0.054.8
Blended price ($/1M)$6.56$10.94
Time to first token (s)0.00s11.69s
aime15.7%
aime 25
artificial analysis coding index30.2048.10
artificial analysis intelligence index15.9052.90
artificial analysis math index
gpqa59.9%89.6%
hle3.9%36.7%
ifbench53.1%
lcr70.7%
livecodebench38.1%
math 50077.1%
mmlu pro77.2%
scicode36.6%51.9%
tau292.1%
terminalbench hard46.2%

Benchmark data from Artificial Analysis.