← All comparisons
DeepSeek V4 Pro (Non-reasoning) vs Molmo2-8B
DeepSeek vs Allen Institute for AI — side-by-side benchmark comparison
| DeepSeek V4 Pro (Non-reasoning) | Molmo2-8B | |
|---|---|---|
| Intelligence Index | 39.3 | 7.3 |
| Coding Index | 38.4 | 4.4 |
| Math Index | — | — |
| Output speed (tok/s) | 53.3 | 0.0 |
| Blended price ($/1M) | $0.54 | $0.00 |
| Time to first token (s) | 1.18s | 0.00s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 38.40 | 4.40 |
| artificial analysis intelligence index | 39.30 | 7.30 |
| artificial analysis math index | — | — |
| gpqa | 71.7% | 42.5% |
| hle | 7.7% | 4.4% |
| ifbench | 45.8% | 26.9% |
| lcr | 45.0% | 0.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 42.4% | 13.3% |
| tau2 | 91.2% | 0.0% |
| terminalbench hard | 36.4% | 0.0% |
Benchmark data from Artificial Analysis.