← All comparisons
Gemini 3.5 Flash (minimal) vs Olmo 3.1 32B Think
Google vs Allen Institute for AI — side-by-side benchmark comparison
| Gemini 3.5 Flash (minimal) | Olmo 3.1 32B Think | |
|---|---|---|
| Intelligence Index | 43.3 | 13.9 |
| Coding Index | 47.1 | 9.8 |
| Math Index | — | 77.3 |
| Output speed (tok/s) | 216.5 | 0.0 |
| Blended price ($/1M) | $3.38 | $0.00 |
| Time to first token (s) | 0.81s | 0.00s |
| aime | — | — |
| aime 25 | — | 77.3% |
| artificial analysis coding index | 47.10 | 9.80 |
| artificial analysis intelligence index | 43.30 | 13.90 |
| artificial analysis math index | — | 77.30 |
| gpqa | 82.8% | 59.1% |
| hle | 23.1% | 6.0% |
| ifbench | 47.3% | 66.0% |
| lcr | 53.3% | 0.0% |
| livecodebench | — | 69.5% |
| math 500 | — | — |
| mmlu pro | — | 76.3% |
| scicode | 48.8% | 29.3% |
| tau2 | 58.8% | 0.0% |
| terminalbench hard | 46.2% | 0.0% |
Benchmark data from Artificial Analysis.