← All comparisons
Molmo 7B-D vs Qwen3 14B (Non-reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Molmo 7B-D | Qwen3 14B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 9.2 | 12.8 |
| Coding Index | 1.2 | 12.4 |
| Math Index | 0.0 | 58.0 |
| Output speed (tok/s) | 0.0 | 64.4 |
| Blended price ($/1M) | $0.00 | $0.38 |
| Time to first token (s) | 0.00s | 1.04s |
| aime | — | 28.0% |
| aime 25 | 0.0% | 58.0% |
| artificial analysis coding index | 1.20 | 12.40 |
| artificial analysis intelligence index | 9.20 | 12.80 |
| artificial analysis math index | 0.0% | 58.00 |
| gpqa | 24.0% | 47.0% |
| hle | 5.1% | 4.2% |
| ifbench | 19.7% | 23.9% |
| lcr | 0.0% | 0.0% |
| livecodebench | 3.9% | 28.0% |
| math 500 | — | 87.1% |
| mmlu pro | 37.1% | 67.5% |
| scicode | 3.6% | 26.5% |
| tau2 | 0.0% | 32.2% |
| terminalbench hard | 0.0% | 5.3% |
Benchmark data from Artificial Analysis.