← All comparisons
Claude Opus 4.5 (Non-reasoning) vs OLMo 2 7B
Anthropic vs Allen Institute for AI — side-by-side benchmark comparison
| Claude Opus 4.5 (Non-reasoning) | OLMo 2 7B | |
|---|---|---|
| Intelligence Index | 43.1 | 9.3 |
| Coding Index | 42.9 | 1.2 |
| Math Index | 62.7 | 0.7 |
| Output speed (tok/s) | 57.0 | 0.0 |
| Blended price ($/1M) | $10.94 | $0.00 |
| Time to first token (s) | 0.93s | 0.00s |
| aime | — | — |
| aime 25 | 62.7% | 0.7% |
| artificial analysis coding index | 42.90 | 1.20 |
| artificial analysis intelligence index | 43.10 | 9.30 |
| artificial analysis math index | 62.70 | 70.0% |
| gpqa | 81.0% | 28.8% |
| hle | 12.9% | 5.5% |
| ifbench | 43.0% | 24.4% |
| lcr | 65.3% | 0.0% |
| livecodebench | 73.8% | 4.1% |
| math 500 | — | — |
| mmlu pro | 88.9% | 28.2% |
| scicode | 47.0% | 3.7% |
| tau2 | 86.3% | 0.0% |
| terminalbench hard | 40.9% | 0.0% |
Benchmark data from Artificial Analysis.