← All comparisons
Olmo 3.1 32B Instruct vs DeepSeek-V2.5
Allen Institute for AI vs DeepSeek — side-by-side benchmark comparison
| Olmo 3.1 32B Instruct | DeepSeek-V2.5 | |
|---|---|---|
| Intelligence Index | 12.2 | 12.3 |
| Coding Index | 5.6 | — |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 5.60 | — |
| artificial analysis intelligence index | 12.20 | 12.30 |
| artificial analysis math index | — | — |
| gpqa | 53.9% | — |
| hle | 4.9% | — |
| ifbench | 39.2% | — |
| lcr | 0.0% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 16.7% | — |
| tau2 | 21.3% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.