← All comparisons
DeepSeek V3.2 (Non-reasoning) vs OLMo 2 7B
DeepSeek vs Allen Institute for AI — side-by-side benchmark comparison
| DeepSeek V3.2 (Non-reasoning) | OLMo 2 7B | |
|---|---|---|
| Intelligence Index | 32.1 | 9.3 |
| Coding Index | 34.6 | 1.2 |
| Math Index | 59.0 | 0.7 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.78 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | 59.0% | 0.7% |
| artificial analysis coding index | 34.60 | 1.20 |
| artificial analysis intelligence index | 32.10 | 9.30 |
| artificial analysis math index | 59.00 | 70.0% |
| gpqa | 75.1% | 28.8% |
| hle | 10.5% | 5.5% |
| ifbench | 49.0% | 24.4% |
| lcr | 39.0% | 0.0% |
| livecodebench | 59.3% | 4.1% |
| math 500 | — | — |
| mmlu pro | 83.7% | 28.2% |
| scicode | 38.7% | 3.7% |
| tau2 | 78.9% | 0.0% |
| terminalbench hard | 32.6% | 0.0% |
Benchmark data from Artificial Analysis.