← All comparisons
Molmo2-8B vs Grok 4.20 0309 (Non-reasoning)
Allen Institute for AI vs xAI — side-by-side benchmark comparison
| Molmo2-8B | Grok 4.20 0309 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 7.3 | 29.7 |
| Coding Index | 4.4 | 25.4 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 202.6 |
| Blended price ($/1M) | $0.00 | $3.00 |
| Time to first token (s) | 0.00s | 0.50s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 4.40 | 25.40 |
| artificial analysis intelligence index | 7.30 | 29.70 |
| artificial analysis math index | — | — |
| gpqa | 42.5% | 78.5% |
| hle | 4.4% | 22.5% |
| ifbench | 26.9% | 47.8% |
| lcr | 0.0% | 18.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 13.3% | 32.2% |
| tau2 | 0.0% | 69.6% |
| terminalbench hard | 0.0% | 22.0% |
Benchmark data from Artificial Analysis.