← All comparisons
Molmo 7B-D vs Grok 3 mini Reasoning (high)
Allen Institute for AI vs xAI — side-by-side benchmark comparison
| Molmo 7B-D | Grok 3 mini Reasoning (high) | |
|---|---|---|
| Intelligence Index | 9.2 | 32.1 |
| Coding Index | 1.2 | 25.2 |
| Math Index | 0.0 | 84.7 |
| Output speed (tok/s) | 0.0 | 56.8 |
| Blended price ($/1M) | $0.00 | $0.35 |
| Time to first token (s) | 0.00s | 0.42s |
| aime | — | 93.3% |
| aime 25 | 0.0% | 84.7% |
| artificial analysis coding index | 1.20 | 25.20 |
| artificial analysis intelligence index | 9.20 | 32.10 |
| artificial analysis math index | 0.0% | 84.70 |
| gpqa | 24.0% | 79.1% |
| hle | 5.1% | 11.1% |
| ifbench | 19.7% | 45.9% |
| lcr | 0.0% | 50.3% |
| livecodebench | 3.9% | 69.6% |
| math 500 | — | 99.2% |
| mmlu pro | 37.1% | 82.8% |
| scicode | 3.6% | 40.6% |
| tau2 | 0.0% | 90.4% |
| terminalbench hard | 0.0% | 17.4% |
Benchmark data from Artificial Analysis.