← All comparisons
GPT-5.1 (Non-reasoning) vs OLMo 2 32B
OpenAI vs Allen Institute for AI — side-by-side benchmark comparison
| GPT-5.1 (Non-reasoning) | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 27.4 | 10.6 |
| Coding Index | 27.3 | 2.7 |
| Math Index | 38.0 | 3.3 |
| Output speed (tok/s) | 129.5 | 0.0 |
| Blended price ($/1M) | $3.44 | $0.00 |
| Time to first token (s) | 0.72s | 0.00s |
| aime | — | — |
| aime 25 | 38.0% | 3.3% |
| artificial analysis coding index | 27.30 | 2.70 |
| artificial analysis intelligence index | 27.40 | 10.60 |
| artificial analysis math index | 38.00 | 3.30 |
| gpqa | 64.3% | 32.8% |
| hle | 5.2% | 3.7% |
| ifbench | 43.2% | 38.1% |
| lcr | 44.0% | 0.0% |
| livecodebench | 49.4% | 6.8% |
| math 500 | — | — |
| mmlu pro | 80.1% | 51.1% |
| scicode | 36.5% | 8.0% |
| tau2 | 46.5% | 0.0% |
| terminalbench hard | 22.7% | 0.0% |
Benchmark data from Artificial Analysis.