← All comparisons
Gemma 4 31B (Reasoning) vs Olmo 3 7B Think
Google vs Allen Institute for AI — side-by-side benchmark comparison
| Gemma 4 31B (Reasoning) | Olmo 3 7B Think | |
|---|---|---|
| Intelligence Index | 39.2 | 9.4 |
| Coding Index | 38.7 | 7.6 |
| Math Index | — | 70.7 |
| Output speed (tok/s) | 35.3 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 1.00s | 0.00s |
| aime | — | — |
| aime 25 | — | 70.7% |
| artificial analysis coding index | 38.70 | 7.60 |
| artificial analysis intelligence index | 39.20 | 9.40 |
| artificial analysis math index | — | 70.70 |
| gpqa | 85.7% | 51.6% |
| hle | 22.7% | 5.7% |
| ifbench | 75.6% | 41.5% |
| lcr | 62.0% | 0.0% |
| livecodebench | — | 61.7% |
| math 500 | — | — |
| mmlu pro | — | 65.5% |
| scicode | 43.4% | 21.2% |
| tau2 | 59.9% | 0.0% |
| terminalbench hard | 36.4% | 0.8% |
Benchmark data from Artificial Analysis.