← All comparisons
DeepSeek V3.1 Terminus (Reasoning) vs OLMo 2 32B
DeepSeek vs Allen Institute for AI — side-by-side benchmark comparison
| DeepSeek V3.1 Terminus (Reasoning) | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 33.9 | 10.6 |
| Coding Index | 33.7 | 2.7 |
| Math Index | 89.7 | 3.3 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $1.91 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | 89.7% | 3.3% |
| artificial analysis coding index | 33.70 | 2.70 |
| artificial analysis intelligence index | 33.90 | 10.60 |
| artificial analysis math index | 89.70 | 3.30 |
| gpqa | 79.2% | 32.8% |
| hle | 15.2% | 3.7% |
| ifbench | 57.0% | 38.1% |
| lcr | 65.0% | 0.0% |
| livecodebench | 79.8% | 6.8% |
| math 500 | — | — |
| mmlu pro | 85.1% | 51.1% |
| scicode | 40.6% | 8.0% |
| tau2 | 37.1% | 0.0% |
| terminalbench hard | 30.3% | 0.0% |
Benchmark data from Artificial Analysis.