← All comparisons

DeepSeek V4 Pro (Reasoning, Max Effort) vs OLMo 2 32B

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

DeepSeek V4 Pro (Reasoning, Max Effort)OLMo 2 32B
Intelligence Index51.510.6
Coding Index47.52.7
Math Index3.3
Output speed (tok/s)51.80.0
Blended price ($/1M)$0.54$0.00
Time to first token (s)1.21s0.00s
aime
aime 253.3%
artificial analysis coding index47.502.70
artificial analysis intelligence index51.5010.60
artificial analysis math index3.30
gpqa88.8%32.8%
hle35.9%3.7%
ifbench76.5%38.1%
lcr66.3%0.0%
livecodebench6.8%
math 500
mmlu pro51.1%
scicode50.0%8.0%
tau296.2%0.0%
terminalbench hard46.2%0.0%

Benchmark data from Artificial Analysis.