← All comparisons
GPT-5.5 (xhigh) vs Olmo 3.1 32B Think
OpenAI vs Allen Institute for AI — side-by-side benchmark comparison
| GPT-5.5 (xhigh) | Olmo 3.1 32B Think | |
|---|---|---|
| Intelligence Index | 60.2 | 13.9 |
| Coding Index | 59.1 | 9.8 |
| Math Index | — | 77.3 |
| Output speed (tok/s) | 58.7 | 0.0 |
| Blended price ($/1M) | $11.25 | $0.00 |
| Time to first token (s) | 37.14s | 0.00s |
| aime | — | — |
| aime 25 | — | 77.3% |
| artificial analysis coding index | 59.10 | 9.80 |
| artificial analysis intelligence index | 60.20 | 13.90 |
| artificial analysis math index | — | 77.30 |
| gpqa | 93.5% | 59.1% |
| hle | 44.3% | 6.0% |
| ifbench | 75.9% | 66.0% |
| lcr | 74.3% | 0.0% |
| livecodebench | — | 69.5% |
| math 500 | — | — |
| mmlu pro | — | 76.3% |
| scicode | 56.1% | 29.3% |
| tau2 | 93.9% | 0.0% |
| terminalbench hard | 60.6% | 0.0% |
Benchmark data from Artificial Analysis.