← All comparisons
Olmo 3.1 32B Instruct vs GPT-5 mini (high)
Allen Institute for AI vs OpenAI — side-by-side benchmark comparison
| Olmo 3.1 32B Instruct | GPT-5 mini (high) | |
|---|---|---|
| Intelligence Index | 12.2 | 41.2 |
| Coding Index | 5.6 | 35.3 |
| Math Index | — | 90.7 |
| Output speed (tok/s) | 0.0 | 96.1 |
| Blended price ($/1M) | $0.00 | $0.69 |
| Time to first token (s) | 0.00s | 77.65s |
| aime | — | — |
| aime 25 | — | 90.7% |
| artificial analysis coding index | 5.60 | 35.30 |
| artificial analysis intelligence index | 12.20 | 41.20 |
| artificial analysis math index | — | 90.70 |
| gpqa | 53.9% | 82.8% |
| hle | 4.9% | 19.7% |
| ifbench | 39.2% | 75.4% |
| lcr | 0.0% | 68.0% |
| livecodebench | — | 83.8% |
| math 500 | — | — |
| mmlu pro | — | 83.7% |
| scicode | 16.7% | 39.2% |
| tau2 | 21.3% | 68.4% |
| terminalbench hard | 0.0% | 33.3% |
Benchmark data from Artificial Analysis.