← All comparisons

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

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude Sonnet 4.6 (Non-reasoning, Low Effort)Claude 3.5 Sonnet (Oct '24)
Intelligence Index42.615.9
Coding Index43.030.2
Math Index
Output speed (tok/s)54.90.0
Blended price ($/1M)$6.56$6.56
Time to first token (s)1.13s0.00s
aime15.7%
aime 25
artificial analysis coding index43.0030.20
artificial analysis intelligence index42.6015.90
artificial analysis math index
gpqa79.7%59.9%
hle10.8%3.9%
ifbench42.4%
lcr58.7%
livecodebench38.1%
math 50077.1%
mmlu pro77.2%
scicode44.1%36.6%
tau278.9%
terminalbench hard42.4%

Benchmark data from Artificial Analysis.