← All comparisons
GPT-5.5 (Non-reasoning) vs Olmo 3.1 32B Instruct
OpenAI vs Allen Institute for AI — side-by-side benchmark comparison
| GPT-5.5 (Non-reasoning) | Olmo 3.1 32B Instruct | |
|---|---|---|
| Intelligence Index | 40.9 | 12.2 |
| Coding Index | 48.6 | 5.6 |
| Math Index | — | — |
| 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 | — | — |
| artificial analysis coding index | 48.60 | 5.60 |
| artificial analysis intelligence index | 40.90 | 12.20 |
| artificial analysis math index | — | — |
| gpqa | 76.8% | 53.9% |
| hle | 12.6% | 4.9% |
| ifbench | 46.1% | 39.2% |
| lcr | 56.3% | 0.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 47.3% | 16.7% |
| tau2 | 69.3% | 21.3% |
| terminalbench hard | 49.2% | 0.0% |
Benchmark data from Artificial Analysis.