← All comparisons
Molmo 7B-D vs GPT-5.1 Codex (high)
Allen Institute for AI vs OpenAI — side-by-side benchmark comparison
| Molmo 7B-D | GPT-5.1 Codex (high) | |
|---|---|---|
| Intelligence Index | 9.2 | 43.1 |
| Coding Index | 1.2 | 36.6 |
| Math Index | 0.0 | 95.7 |
| Output speed (tok/s) | 0.0 | 182.1 |
| Blended price ($/1M) | $0.00 | $3.44 |
| Time to first token (s) | 0.00s | 5.42s |
| aime | — | — |
| aime 25 | 0.0% | 95.7% |
| artificial analysis coding index | 1.20 | 36.60 |
| artificial analysis intelligence index | 9.20 | 43.10 |
| artificial analysis math index | 0.0% | 95.70 |
| gpqa | 24.0% | 86.0% |
| hle | 5.1% | 23.4% |
| ifbench | 19.7% | 70.0% |
| lcr | 0.0% | 67.3% |
| livecodebench | 3.9% | 84.9% |
| math 500 | — | — |
| mmlu pro | 37.1% | 86.0% |
| scicode | 3.6% | 40.2% |
| tau2 | 0.0% | 83.0% |
| terminalbench hard | 0.0% | 34.8% |
Benchmark data from Artificial Analysis.