← All comparisons

Olmo 3.1 32B Think vs DeepSeek Coder V2 Lite Instruct

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

Olmo 3.1 32B ThinkDeepSeek Coder V2 Lite Instruct
Intelligence Index13.98.5
Coding Index9.8—
Math Index77.3—
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$0.00
Time to first token (s)0.00s0.00s
aime——
aime 2577.3%—
artificial analysis coding index9.80—
artificial analysis intelligence index13.908.50
artificial analysis math index77.30—
gpqa59.1%31.9%
hle6.0%5.3%
ifbench66.0%—
lcr0.0%—
livecodebench69.5%15.8%
math 500——
mmlu pro76.3%42.9%
scicode29.3%13.9%
tau20.0%—
terminalbench hard0.0%—

Benchmark data from Artificial Analysis.