Model
Step 3.7 Flash
StepFun
Knowledge & Reasoning
Knowledge & ReasoningCoding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Hob-VL | 14.6 | comparison_against_published_performance_metrics_of_specialist_models | N/A | Independent | medium | arxiv.org |
| SciCode | 40.0 | score | N/A | Independent | medium | artificialanalysis.ai |
Reproduced by the community
Loading community runs…