← All comparisons
DeepSeek R1 0528 (May '25) vs Olmo 3 32B Think
DeepSeek vs Allen Institute for AI — side-by-side benchmark comparison
| DeepSeek R1 0528 (May '25) | Olmo 3 32B Think | |
|---|---|---|
| Intelligence Index | 27.1 | 12.1 |
| Coding Index | 24.0 | 10.5 |
| Math Index | 76.0 | 73.7 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $2.06 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 89.3% | — |
| aime 25 | 76.0% | 73.7% |
| artificial analysis coding index | 24.00 | 10.50 |
| artificial analysis intelligence index | 27.10 | 12.10 |
| artificial analysis math index | 76.00 | 73.70 |
| gpqa | 81.3% | 61.0% |
| hle | 14.9% | 5.9% |
| ifbench | 39.6% | 49.1% |
| lcr | 54.7% | 0.0% |
| livecodebench | 77.0% | 67.2% |
| math 500 | 98.3% | — |
| mmlu pro | 84.9% | 75.9% |
| scicode | 40.3% | 28.6% |
| tau2 | 36.5% | 0.0% |
| terminalbench hard | 15.9% | 1.5% |
Benchmark data from Artificial Analysis.