← All comparisons
Olmo 3 7B Instruct vs Gemini 2.5 Flash-Lite (Reasoning)
Allen Institute for AI vs Google — side-by-side benchmark comparison
| Olmo 3 7B Instruct | Gemini 2.5 Flash-Lite (Reasoning) | |
|---|---|---|
| Intelligence Index | 8.1 | 17.6 |
| Coding Index | 3.4 | 9.5 |
| Math Index | 41.3 | 53.3 |
| Output speed (tok/s) | 0.0 | 275.9 |
| Blended price ($/1M) | $0.13 | $0.17 |
| Time to first token (s) | 0.00s | 17.31s |
| aime | — | 70.3% |
| aime 25 | 41.3% | 53.3% |
| artificial analysis coding index | 3.40 | 9.50 |
| artificial analysis intelligence index | 8.10 | 17.60 |
| artificial analysis math index | 41.30 | 53.30 |
| gpqa | 40.0% | 62.5% |
| hle | 5.8% | 6.4% |
| ifbench | 32.8% | 49.9% |
| lcr | 0.0% | 51.3% |
| livecodebench | 26.6% | 59.3% |
| math 500 | — | 96.9% |
| mmlu pro | 52.2% | 75.9% |
| scicode | 10.3% | 19.3% |
| tau2 | 12.6% | 18.4% |
| terminalbench hard | 0.0% | 4.5% |
Benchmark data from Artificial Analysis.