← All comparisons
Olmo 3 7B Instruct vs GPT-5 mini (high)
Allen Institute for AI vs OpenAI — side-by-side benchmark comparison
| Olmo 3 7B Instruct | GPT-5 mini (high) | |
|---|---|---|
| Intelligence Index | 8.1 | 41.2 |
| Coding Index | 3.4 | 35.3 |
| Math Index | 41.3 | 90.7 |
| Output speed (tok/s) | 0.0 | 96.1 |
| Blended price ($/1M) | $0.13 | $0.69 |
| Time to first token (s) | 0.00s | 77.65s |
| aime | — | — |
| aime 25 | 41.3% | 90.7% |
| artificial analysis coding index | 3.40 | 35.30 |
| artificial analysis intelligence index | 8.10 | 41.20 |
| artificial analysis math index | 41.30 | 90.70 |
| gpqa | 40.0% | 82.8% |
| hle | 5.8% | 19.7% |
| ifbench | 32.8% | 75.4% |
| lcr | 0.0% | 68.0% |
| livecodebench | 26.6% | 83.8% |
| math 500 | — | — |
| mmlu pro | 52.2% | 83.7% |
| scicode | 10.3% | 39.2% |
| tau2 | 12.6% | 68.4% |
| terminalbench hard | 0.0% | 33.3% |
Benchmark data from Artificial Analysis.