imo_gradingbench.yaml

imo_gradingbench:
  resources_servers:
    imo_gradingbench:
      entrypoint: app.py
      domain: math
      verified: false
      description: "Four-class grading of math proofs — the policy model reads a problem plus a candidate proof and emits one of correct / almost / partial / incorrect as the last word."
      value: "Improve the IMO-GradingBench benchmark and proof-grading skill."

imo_gradingbench_simple_agent:
  responses_api_agents:
    simple_agent:
      entrypoint: app.py
      resources_server:
        type: resources_servers
        name: imo_gradingbench
      model_server:
        type: responses_api_models
        name: policy_model
      datasets:
        - name: example
          type: example
          jsonl_fpath: resources_servers/imo_gradingbench/data/example.jsonl