llm-lab Report

Run df0c8ed1379c · offline-demo-v1
PASS
offline-demo-v1
evaluate offline demo: return a deterministic auditable answer
5
185
$0.0
#ActionVerdictTokensCost
1 load_prompt_set PASS 37 $0.0
2 call_model PASS 37 $0.0
3 collect_outputs PASS 37 $0.0
4 run_verifier PASS 37 $0.0
5 aggregate_metrics PASS 37 $0.0
[
  {
    "action": "load_prompt_set",
    "prompt": "evaluate offline demo: return a deterministic auditable answer",
    "output": "OFFLINE_DEMO_PASS prompt_sha256=7633cd95d0df1824 verification=deterministic route=offline",
    "model": "offline-demo-v1",
    "verdict": {
      "label": "pass",
      "reason": "non-empty output"
    },
    "tokens": 37,
    "cost": 0.0,
    "metric_check": null
  },
  {
    "action": "call_model",
    "prompt": "evaluate offline demo: return a deterministic auditable answer",
    "output": "OFFLINE_DEMO_PASS prompt_sha256=7633cd95d0df1824 verification=deterministic route=offline",
    "model": "offline-demo-v1",
    "verdict": {
      "label": "pass",
      "reason": "non-empty output"
    },
    "tokens": 37,
    "cost": 0.0,
    "metric_check": null
  },
  {
    "action": "collect_outputs",
    "prompt": "evaluate offline demo: return a deterministic auditable answer",
    "output": "OFFLINE_DEMO_PASS prompt_sha256=7633cd95d0df1824 verification=deterministic route=offline",
    "model": "offline-demo-v1",
    "verdict": {
      "label": "pass",
      "reason": "non-empty output"
    },
    "tokens": 37,
    "cost": 0.0,
    "metric_check": null
  },
  {
    "action": "run_verifier",
    "prompt": "evaluate offline demo: return a deterministic auditable answer",
    "output": "OFFLINE_DEMO_PASS prompt_sha256=7633cd95d0df1824 verification=deterministic route=offline",
    "model": "offline-demo-v1",
    "verdict": {
      "label": "pass",
      "reason": "non-empty output"
    },
    "tokens": 37,
    "cost": 0.0,
    "metric_check": null
  },
  {
    "action": "aggregate_metrics",
    "prompt": "evaluate offline demo: return a deterministic auditable answer",
    "output": "OFFLINE_DEMO_PASS prompt_sha256=7633cd95d0df1824 verification=deterministic route=offline",
    "model": "offline-demo-v1",
    "verdict": {
      "label": "pass",
      "reason": "non-empty output"
    },
    "tokens": 37,
    "cost": 0.0,
    "metric_check": null
  }
]