← All comparisons
GPT-5.3 Codex (xhigh) vs Molmo 7B-D
OpenAI vs Allen Institute for AI — side-by-side benchmark comparison
| GPT-5.3 Codex (xhigh) | Molmo 7B-D | |
|---|---|---|
| Intelligence Index | 53.6 | 9.2 |
| Coding Index | 53.1 | 1.2 |
| Math Index | — | 0.0 |
| Output speed (tok/s) | 84.7 | 0.0 |
| Blended price ($/1M) | $4.81 | $0.00 |
| Time to first token (s) | 60.27s | 0.00s |
| aime | — | — |
| aime 25 | — | 0.0% |
| artificial analysis coding index | 53.10 | 1.20 |
| artificial analysis intelligence index | 53.60 | 9.20 |
| artificial analysis math index | — | 0.0% |
| gpqa | 91.5% | 24.0% |
| hle | 39.9% | 5.1% |
| ifbench | 75.4% | 19.7% |
| lcr | 74.0% | 0.0% |
| livecodebench | — | 3.9% |
| math 500 | — | — |
| mmlu pro | — | 37.1% |
| scicode | 53.2% | 3.6% |
| tau2 | 86.0% | 0.0% |
| terminalbench hard | 53.0% | 0.0% |
Benchmark data from Artificial Analysis.