← All comparisons
Molmo2-8B vs Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Allen Institute for AI vs Anthropic — side-by-side benchmark comparison
| Molmo2-8B | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | |
|---|---|---|
| Intelligence Index | 7.3 | 52.9 |
| Coding Index | 4.4 | 48.1 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 54.8 |
| Blended price ($/1M) | $0.00 | $10.94 |
| Time to first token (s) | 0.00s | 11.69s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 4.40 | 48.10 |
| artificial analysis intelligence index | 7.30 | 52.90 |
| artificial analysis math index | — | — |
| gpqa | 42.5% | 89.6% |
| hle | 4.4% | 36.7% |
| ifbench | 26.9% | 53.1% |
| lcr | 0.0% | 70.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 13.3% | 51.9% |
| tau2 | 0.0% | 92.1% |
| terminalbench hard | 0.0% | 46.2% |
Benchmark data from Artificial Analysis.