← All comparisons

Olmo 3 7B Think vs GPT-5.2 Codex (xhigh)

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

Olmo 3 7B ThinkGPT-5.2 Codex (xhigh)
Intelligence Index9.449.0
Coding Index7.643.0
Math Index70.7—
Output speed (tok/s)0.0111.3
Blended price ($/1M)$0.00$4.81
Time to first token (s)0.00s1.33s
aime——
aime 2570.7%—
artificial analysis coding index7.6043.00
artificial analysis intelligence index9.4049.00
artificial analysis math index70.70—
gpqa51.6%89.9%
hle5.7%33.5%
ifbench41.5%77.6%
lcr0.0%75.7%
livecodebench61.7%—
math 500——
mmlu pro65.5%—
scicode21.2%54.6%
tau20.0%92.1%
terminalbench hard0.8%37.1%

Benchmark data from Artificial Analysis.