← All comparisons
Olmo 3.1 32B Think vs GPT-5.2 (medium)
Allen Institute for AI vs OpenAI — side-by-side benchmark comparison
| Olmo 3.1 32B Think | GPT-5.2 (medium) | |
|---|---|---|
| Intelligence Index | 13.9 | 46.6 |
| Coding Index | 9.8 | 44.2 |
| Math Index | 77.3 | 96.7 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $4.81 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | 77.3% | 96.7% |
| artificial analysis coding index | 9.80 | 44.20 |
| artificial analysis intelligence index | 13.90 | 46.60 |
| artificial analysis math index | 77.30 | 96.70 |
| gpqa | 59.1% | 86.4% |
| hle | 6.0% | 24.9% |
| ifbench | 66.0% | 65.2% |
| lcr | 0.0% | 63.3% |
| livecodebench | 69.5% | 89.4% |
| math 500 | — | — |
| mmlu pro | 76.3% | 85.9% |
| scicode | 29.3% | 46.2% |
| tau2 | 0.0% | 74.3% |
| terminalbench hard | 0.0% | 43.2% |
Benchmark data from Artificial Analysis.