← All comparisons
Molmo 7B-D vs Claude Opus 4.5 (Reasoning)
Allen Institute for AI vs Anthropic — side-by-side benchmark comparison
| Molmo 7B-D | Claude Opus 4.5 (Reasoning) | |
|---|---|---|
| Intelligence Index | 9.2 | 49.7 |
| Coding Index | 1.2 | 47.8 |
| Math Index | 0.0 | 91.3 |
| Output speed (tok/s) | 0.0 | 73.2 |
| Blended price ($/1M) | $0.00 | $10.94 |
| Time to first token (s) | 0.00s | 11.69s |
| aime | — | — |
| aime 25 | 0.0% | 91.3% |
| artificial analysis coding index | 1.20 | 47.80 |
| artificial analysis intelligence index | 9.20 | 49.70 |
| artificial analysis math index | 0.0% | 91.30 |
| gpqa | 24.0% | 86.6% |
| hle | 5.1% | 28.4% |
| ifbench | 19.7% | 58.0% |
| lcr | 0.0% | 74.0% |
| livecodebench | 3.9% | 87.1% |
| math 500 | — | — |
| mmlu pro | 37.1% | 89.5% |
| scicode | 3.6% | 49.5% |
| tau2 | 0.0% | 89.5% |
| terminalbench hard | 0.0% | 47.0% |
Benchmark data from Artificial Analysis.