← All comparisons
Olmo 3 7B Think vs GPT-5 (high)
Allen Institute for AI vs OpenAI — side-by-side benchmark comparison
| Olmo 3 7B Think | GPT-5 (high) | |
|---|---|---|
| Intelligence Index | 9.4 | 44.6 |
| Coding Index | 7.6 | 36.0 |
| Math Index | 70.7 | 94.3 |
| Output speed (tok/s) | 0.0 | 104.0 |
| Blended price ($/1M) | $0.00 | $3.44 |
| Time to first token (s) | 0.00s | 82.62s |
| aime | — | 95.7% |
| aime 25 | 70.7% | 94.3% |
| artificial analysis coding index | 7.60 | 36.00 |
| artificial analysis intelligence index | 9.40 | 44.60 |
| artificial analysis math index | 70.70 | 94.30 |
| gpqa | 51.6% | 85.4% |
| hle | 5.7% | 26.5% |
| ifbench | 41.5% | 73.1% |
| lcr | 0.0% | 75.6% |
| livecodebench | 61.7% | 84.6% |
| math 500 | — | 99.4% |
| mmlu pro | 65.5% | 87.1% |
| scicode | 21.2% | 42.9% |
| tau2 | 0.0% | 84.8% |
| terminalbench hard | 0.8% | 32.6% |
Benchmark data from Artificial Analysis.