← All comparisons
Olmo 3.1 32B Instruct vs GPT-4.1 mini
Allen Institute for AI vs OpenAI — side-by-side benchmark comparison
| Olmo 3.1 32B Instruct | GPT-4.1 mini | |
|---|---|---|
| Intelligence Index | 12.2 | 22.9 |
| Coding Index | 5.6 | 18.5 |
| Math Index | — | 46.3 |
| Output speed (tok/s) | 0.0 | 95.1 |
| Blended price ($/1M) | $0.00 | $0.70 |
| Time to first token (s) | 0.00s | 0.59s |
| aime | — | 43.0% |
| aime 25 | — | 46.3% |
| artificial analysis coding index | 5.60 | 18.50 |
| artificial analysis intelligence index | 12.20 | 22.90 |
| artificial analysis math index | — | 46.30 |
| gpqa | 53.9% | 66.4% |
| hle | 4.9% | 4.6% |
| ifbench | 39.2% | 38.3% |
| lcr | 0.0% | 42.3% |
| livecodebench | — | 48.3% |
| math 500 | — | 92.5% |
| mmlu pro | — | 78.1% |
| scicode | 16.7% | 40.4% |
| tau2 | 21.3% | 52.9% |
| terminalbench hard | 0.0% | 7.6% |
Benchmark data from Artificial Analysis.