voicebench: resources_servers: voicebench: entrypoint: app.py domain: e2e verified: false description: Synthetic text smoke examples for the VoiceBench legacy MCQ scorer subset: openbookqa scoring_type: mcq scoring_version: legacy_v1 seed: null expected_num_rows: 5 expected_sample_ids_file: null judge_model_server: null judge_prompt_file: null judge_temperature: 0.5 judge_top_p: 0.95 judge_max_tokens: 1024 judge_n: 3 judge_max_concurrency: 40 voicebench_simple_agent: responses_api_agents: simple_agent: entrypoint: app.py resources_server: type: resources_servers name: voicebench model_server: type: responses_api_models name: policy_model datasets: - name: example type: example jsonl_fpath: resources_servers/voicebench/data/example.jsonl license: Apache 2.0 voicebench_environment_server: environment_servers: single_agent_turn_legacy: entrypoint: app.py resources_server: type: resources_servers name: voicebench agent_server: type: responses_api_agents name: voicebench_simple_agent resources_tool_transports: - direct_http