← All comparisons
Command A vs OLMo 2 32B
Cohere vs Allen Institute for AI — side-by-side benchmark comparison
| Command A | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 13.5 | 10.6 |
| Coding Index | 9.9 | 2.7 |
| Math Index | 13.0 | 3.3 |
| Output speed (tok/s) | 53.0 | 0.0 |
| Blended price ($/1M) | $4.38 | $0.00 |
| Time to first token (s) | 0.45s | 0.00s |
| aime | 9.7% | — |
| aime 25 | 13.0% | 3.3% |
| artificial analysis coding index | 9.90 | 2.70 |
| artificial analysis intelligence index | 13.50 | 10.60 |
| artificial analysis math index | 13.00 | 3.30 |
| gpqa | 52.7% | 32.8% |
| hle | 4.6% | 3.7% |
| ifbench | 36.5% | 38.1% |
| lcr | 18.0% | 0.0% |
| livecodebench | 28.7% | 6.8% |
| math 500 | 81.9% | — |
| mmlu pro | 71.2% | 51.1% |
| scicode | 28.1% | 8.0% |
| tau2 | 15.2% | 0.0% |
| terminalbench hard | 0.8% | 0.0% |
Benchmark data from Artificial Analysis.