← All comparisons

Olmo 3.1 32B Think vs Claude 4.5 Sonnet (Reasoning)

Allen Institute for AI vs Anthropic — side-by-side benchmark comparison

Olmo 3.1 32B ThinkClaude 4.5 Sonnet (Reasoning)
Intelligence Index13.943.0
Coding Index9.838.6
Math Index77.388.0
Output speed (tok/s)0.055.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s7.02s
aime——
aime 2577.3%88.0%
artificial analysis coding index9.8038.60
artificial analysis intelligence index13.9043.00
artificial analysis math index77.3088.00
gpqa59.1%83.4%
hle6.0%17.3%
ifbench66.0%57.3%
lcr0.0%65.7%
livecodebench69.5%71.4%
math 500——
mmlu pro76.3%87.5%
scicode29.3%44.7%
tau20.0%78.1%
terminalbench hard0.0%35.6%

Benchmark data from Artificial Analysis.