iop/scripts/fixtures/agent-comparison-benchmark-supported-direct.example.json
toki 029ff0d2c8 feat(benchmark): 비교 파이프라인을 완성한다
동일한 IOP 경유 과업을 caller와 model 설정만 바꿔 재현하고, 실패를 포함한 실행·검증·채점 근거를 보존할 수 있어야 한다.
2026-08-12 01:44:26 +09:00

96 lines
2.8 KiB
JSON

{
"pipeline_version": "2",
"environment": "dev",
"testbed": "../iop-s2",
"repetitions": 1,
"session_policy": "fresh",
"setup_cache_policy": "isolated",
"timeout": {
"run_seconds": 300,
"idle_seconds": 30,
"quiet_seconds": 10,
"cleanup_grace_seconds": 5
},
"viewports": [
{"id": "desktop_1080", "width": 1920, "height": 1080},
{"id": "mobile_375", "width": 375, "height": 812}
],
"rubric_version": "landing-quality-v1",
"evaluator": {
"caller": "codex",
"iop": {
"request_model": "gpt-5.6-luna",
"requested_effort": "xhigh",
"route_kind": "direct",
"route_id": "gpt-5.6-luna",
"expected_bindings": [
{"stage": "request", "model": "gpt-5.6-luna", "effort": "xhigh"}
]
}
},
"output_root": "agent-test/runs/bench-01-supported-direct",
"fixture": {
"version": "landing-v1",
"prompt": "scripts/fixtures/agent-comparison-benchmark/prompt.md",
"assets": [
{"source": "scripts/fixtures/agent-comparison-benchmark/reference.txt", "workspace_path": "brief/reference.txt"},
{"source": "scripts/fixtures/agent-comparison-benchmark/aurora-grid.svg", "workspace_path": "assets/aurora-grid.svg"},
{"source": "scripts/fixtures/agent-comparison-benchmark/orbit-rings.svg", "workspace_path": "assets/orbit-rings.svg"}
],
"checksum": "sha256:7dc1be6ed4a9f2f873016b708b99d827b0249c74f2ac287e1fcf8deade8dcd98"
},
"matrix": [
{
"id": "claude-sonnet-direct",
"caller": "claude",
"iop": {
"request_model": "claude-sonnet-5",
"requested_effort": "max",
"route_kind": "direct",
"route_id": "claude-sonnet-5",
"expected_bindings": [
{"stage": "request", "model": "claude-sonnet-5", "effort": "max"}
]
}
},
{
"id": "claude-gemini-direct",
"caller": "claude",
"iop": {
"request_model": "gemini-3.6-flash",
"requested_effort": "high",
"route_kind": "direct",
"route_id": "gemini-3.6-flash",
"expected_bindings": [
{"stage": "request", "model": "gemini-3.6-flash", "effort": "high"}
]
}
},
{
"id": "claude-gpt-direct",
"caller": "claude",
"iop": {
"request_model": "gpt-5.6-luna",
"requested_effort": "xhigh",
"route_kind": "direct",
"route_id": "gpt-5.6-luna",
"expected_bindings": [
{"stage": "request", "model": "gpt-5.6-luna", "effort": "xhigh"}
]
}
},
{
"id": "codex-gpt-direct",
"caller": "codex",
"iop": {
"request_model": "gpt-5.6-luna",
"requested_effort": "xhigh",
"route_kind": "direct",
"route_id": "gpt-5.6-luna",
"expected_bindings": [
{"stage": "request", "model": "gpt-5.6-luna", "effort": "xhigh"}
]
}
}
]
}