← All comparisons
Step 3.5 Flash 2603 vs OLMo 2 32B
StepFun vs Allen Institute for AI — side-by-side benchmark comparison
| Step 3.5 Flash 2603 | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 38.5 | 10.6 |
| Coding Index | 34.6 | 2.7 |
| Math Index | — | 3.3 |
| Output speed (tok/s) | 167.8 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.88s | 0.00s |
| aime | — | — |
| aime 25 | — | 3.3% |
| artificial analysis coding index | 34.60 | 2.70 |
| artificial analysis intelligence index | 38.50 | 10.60 |
| artificial analysis math index | — | 3.30 |
| gpqa | 82.6% | 32.8% |
| hle | 22.6% | 3.7% |
| ifbench | 66.5% | 38.1% |
| lcr | 54.3% | 0.0% |
| livecodebench | — | 6.8% |
| math 500 | — | — |
| mmlu pro | — | 51.1% |
| scicode | 38.5% | 8.0% |
| tau2 | 87.4% | 0.0% |
| terminalbench hard | 32.6% | 0.0% |
Benchmark data from Artificial Analysis.