← All comparisons
Gemini 2.5 Flash (Non-reasoning) vs OLMo 2 32B
Google vs Allen Institute for AI — side-by-side benchmark comparison
| Gemini 2.5 Flash (Non-reasoning) | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 20.6 | 10.6 |
| Coding Index | 17.8 | 2.7 |
| Math Index | 60.3 | 3.3 |
| Output speed (tok/s) | 214.5 | 0.0 |
| Blended price ($/1M) | $0.85 | $0.00 |
| Time to first token (s) | 0.51s | 0.00s |
| aime | 50.0% | — |
| aime 25 | 60.3% | 3.3% |
| artificial analysis coding index | 17.80 | 2.70 |
| artificial analysis intelligence index | 20.60 | 10.60 |
| artificial analysis math index | 60.30 | 3.30 |
| gpqa | 68.3% | 32.8% |
| hle | 5.1% | 3.7% |
| ifbench | 39.0% | 38.1% |
| lcr | 45.9% | 0.0% |
| livecodebench | 49.5% | 6.8% |
| math 500 | 93.2% | — |
| mmlu pro | 80.9% | 51.1% |
| scicode | 29.1% | 8.0% |
| tau2 | 14.9% | 0.0% |
| terminalbench hard | 12.1% | 0.0% |
Benchmark data from Artificial Analysis.