Model
Step3-VL-10B
StepFun
Agentic / Tool Use
Agentic / Tool UseMultimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Game2Real-Bench | 24.2 | accuracy | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…