← All comparisons
Olmo 3.1 32B Instruct vs DeepSeek V3.1 Terminus (Non-reasoning)
Allen Institute for AI vs DeepSeek — side-by-side benchmark comparison
| Olmo 3.1 32B Instruct | DeepSeek V3.1 Terminus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 12.2 | 28.5 |
| Coding Index | 5.6 | 31.9 |
| Math Index | — | 53.7 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.45 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | — | 53.7% |
| artificial analysis coding index | 5.60 | 31.90 |
| artificial analysis intelligence index | 12.20 | 28.50 |
| artificial analysis math index | — | 53.70 |
| gpqa | 53.9% | 75.1% |
| hle | 4.9% | 8.4% |
| ifbench | 39.2% | 41.2% |
| lcr | 0.0% | 43.3% |
| livecodebench | — | 52.9% |
| math 500 | — | — |
| mmlu pro | — | 83.6% |
| scicode | 16.7% | 32.1% |
| tau2 | 21.3% | 37.1% |
| terminalbench hard | 0.0% | 31.8% |
Benchmark data from Artificial Analysis.