← All comparisons
Step3 VL 10B vs Claude 3.5 Sonnet (Oct '24)
StepFun vs Anthropic — side-by-side benchmark comparison
| Step3 VL 10B | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 15.5 | 15.9 |
| Coding Index | 13.9 | 30.2 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $6.56 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | 15.7% |
| aime 25 | — | — |
| artificial analysis coding index | 13.90 | 30.20 |
| artificial analysis intelligence index | 15.50 | 15.90 |
| artificial analysis math index | — | — |
| gpqa | 69.0% | 59.9% |
| hle | 10.2% | 3.9% |
| ifbench | 50.2% | — |
| lcr | 0.0% | — |
| livecodebench | — | 38.1% |
| math 500 | — | 77.1% |
| mmlu pro | — | 77.2% |
| scicode | 31.1% | 36.6% |
| tau2 | 16.1% | — |
| terminalbench hard | 5.3% | — |
Benchmark data from Artificial Analysis.