← All comparisons
DeepSeek V3 (Dec '24) vs OLMo 2 32B
DeepSeek vs Allen Institute for AI — side-by-side benchmark comparison
| DeepSeek V3 (Dec '24) | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 16.5 | 10.6 |
| Coding Index | 16.4 | 2.7 |
| Math Index | 26.0 | 3.3 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.52 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 25.3% | — |
| aime 25 | 26.0% | 3.3% |
| artificial analysis coding index | 16.40 | 2.70 |
| artificial analysis intelligence index | 16.50 | 10.60 |
| artificial analysis math index | 26.00 | 3.30 |
| gpqa | 55.7% | 32.8% |
| hle | 3.6% | 3.7% |
| ifbench | 34.8% | 38.1% |
| lcr | 29.0% | 0.0% |
| livecodebench | 35.9% | 6.8% |
| math 500 | 88.7% | — |
| mmlu pro | 75.2% | 51.1% |
| scicode | 35.4% | 8.0% |
| tau2 | 22.8% | 0.0% |
| terminalbench hard | 6.8% | 0.0% |
Benchmark data from Artificial Analysis.