Spaces:

RomeroLab-Duke
/

BioDesignBench-Leaderboard

Running

App Files Files Community

BioDesignBench-Leaderboard

Ctrl+K

Ctrl+K

2 contributors

History: 26 commits

Jasonkim8652

align jargon with paper; set organization to RomeroLab

dcf17b1 5 days ago

llm_judge
Phase A: integrate LLM judge panel for hybrid scoring about 1 month ago
.gitattributes

1.52 kB
initial commit 2 months ago
README.md

5.86 kB
align jargon with paper; set organization to RomeroLab 5 days ago
app.py

79.3 kB
align jargon with paper; set organization to RomeroLab 5 days ago
eval_agent.py

16.5 kB
Phase X: contamination-safe submission flow (we host the agent) about 1 month ago
eval_boltz.py

8.09 kB
Phase B (live): Boltz-2 via Modal sidecar instead of ZeroGPU about 1 month ago
eval_dispatcher.py

9.65 kB
Phase X: contamination-safe submission flow (we host the agent) about 1 month ago
eval_judge.py

5.26 kB
Phase A: integrate LLM judge panel for hybrid scoring about 1 month ago
eval_queue.py

10.9 kB
Phase X: contamination-safe submission flow (we host the agent) about 1 month ago
eval_scorer.py

64 kB
Phase A: integrate LLM judge panel for hybrid scoring about 1 month ago
eval_tasks.py

8.31 kB
Phase X: contamination-safe submission flow (we host the agent) about 1 month ago
example_mcp_server.py

4.83 kB
docs: custom MCP guide + minimal FastAPI stub about 1 month ago
leaderboard_data.json

14.8 kB
align jargon with paper; set organization to RomeroLab 5 days ago
mcp_tool_schemas.json

12.6 kB
feat: add submission & scoring infrastructure (eval_scorer, dispatcher, boltz, queue, tasks) + fix gradio 5.x for Python 3.13 2 months ago
modal_boltz_app.py

8.78 kB
Phase B (live): Boltz-2 via Modal sidecar instead of ZeroGPU about 1 month ago
requirements.txt

403 Bytes
Phase B (live): Boltz-2 via Modal sidecar instead of ZeroGPU about 1 month ago