Hardware Execution on Subset B Hardware Execution
0.653ScodeBioProAgent
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| BioProAgentBackbone=Gemini-3-Flash2026.03 | 0.653 | 0.956 | 0.61 | |
| DirectBackbone=GPT-4o2026.03 | 0.59 | 0.995 | 0.295 | |
| DirectBackbone=Gemini-3-Flash2026.03 | 0.576 | 0.996 | 0.287 | |
| AutoGPTBackbone=Gemini-3-Flash2026.03 | 0.54 | 0.911 | 0.468 | |
| DirectBackbone=DeepSeek-V32026.03 | 0.495 | 0.995 | 0.205 | |
| ReflexionBackbone=Gemini-3-Flash2026.03 | 0.278 | 0.534 | 0.403 | |
| ReActBackbone=Gemini-3-Flash2026.03 | 0.038 | 0.21 | 0.103 |