← All comparisons
Olmo 3.1 32B Think vs GPT-4o (Nov '24)
Allen Institute for AI vs OpenAI — side-by-side benchmark comparison
| Olmo 3.1 32B Think | GPT-4o (Nov '24) | |
|---|---|---|
| Intelligence Index | 13.9 | 17.3 |
| Coding Index | 9.8 | 16.7 |
| Math Index | 77.3 | 6.0 |
| Output speed (tok/s) | 0.0 | 158.5 |
| Blended price ($/1M) | $0.00 | $4.38 |
| Time to first token (s) | 0.00s | 0.54s |
| aime | — | 15.0% |
| aime 25 | 77.3% | 6.0% |
| artificial analysis coding index | 9.80 | 16.70 |
| artificial analysis intelligence index | 13.90 | 17.30 |
| artificial analysis math index | 77.30 | 6.00 |
| gpqa | 59.1% | 54.3% |
| hle | 6.0% | 3.3% |
| ifbench | 66.0% | 34.3% |
| lcr | 0.0% | 0.0% |
| livecodebench | 69.5% | 30.9% |
| math 500 | — | 75.9% |
| mmlu pro | 76.3% | 74.8% |
| scicode | 29.3% | 33.3% |
| tau2 | 0.0% | 25.1% |
| terminalbench hard | 0.0% | 8.3% |
Benchmark data from Artificial Analysis.