← All comparisons
GPT-5.5 (Non-reasoning) vs Olmo 3.1 32B Think
OpenAI vs Allen Institute for AI — side-by-side benchmark comparison
| GPT-5.5 (Non-reasoning) | Olmo 3.1 32B Think | |
|---|---|---|
| Intelligence Index | 40.9 | 13.9 |
| Coding Index | 48.6 | 9.8 |
| Math Index | — | 77.3 |
| Output speed (tok/s) | 59.0 | 0.0 |
| Blended price ($/1M) | $11.25 | $0.00 |
| Time to first token (s) | 0.91s | 0.00s |
| aime | — | — |
| aime 25 | — | 77.3% |
| artificial analysis coding index | 48.60 | 9.80 |
| artificial analysis intelligence index | 40.90 | 13.90 |
| artificial analysis math index | — | 77.30 |
| gpqa | 76.8% | 59.1% |
| hle | 12.6% | 6.0% |
| ifbench | 46.1% | 66.0% |
| lcr | 56.3% | 0.0% |
| livecodebench | — | 69.5% |
| math 500 | — | — |
| mmlu pro | — | 76.3% |
| scicode | 47.3% | 29.3% |
| tau2 | 69.3% | 0.0% |
| terminalbench hard | 49.2% | 0.0% |
Benchmark data from Artificial Analysis.