paperclip-runner evalsstatic evidence

← Overview

Agent registers an inspectable deliverable

register-deliverable

The agent registers exactly one artifact and work product from explicit metadata.

Prompt

Register one deliverable for this task titled Orientation evidence using filename orientation.json, content type application/json, byte size 512, sha256 aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa, and content reference fixture://orientation-evidence.

Fixture

../fixtures/companies/orientation.json

Authority

{
  "actorId": "actor-engineer",
  "capabilities": [],
  "explicitClaims": [],
  "taskId": "task-orientation"
}

Current results

ModelConfigurationResultEstimated costRun time
claude-sonnet-5live-acpx-0.13.1-claude-acp-0.70.0-sonnet-5INFRAunknown2026-09-06T20:52:26.471Z
claude-sonnet-5live-claude-managed-agents-2026-04-01-sonnet-5PASS$0.028824 estimated2026-09-06T20:52:25.984Z
global.anthropic.claude-sonnet-4-6live-aws-agentcore-global-anthropic-claude-sonnet-4-6INFRAunknown2026-09-06T20:53:25.430Z
gpt-5.4-minilive-codex-pinnedINFRAunknownunknown
gpt-5.6-sollive-acpx-0.13.1-codex-acp-1.6.2-controlNot run——
openrouter/anthropic/claude-sonnet-5live-opencode-1.18.17-openrouter-claude-sonnet-5PASS$0.018972 estimated2026-09-06T20:54:31.101Z
openrouter/deepseek/deepseek-v4-flash-0731live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731PASS$0.000415 estimated2026-09-06T20:58:16.888Z
openrouter/google/gemini-3.8-flashlive-opencode-1.18.17-openrouter-gemini-3.8-flashPASS$0.024160 estimated2026-09-06T20:55:25.953Z
openrouter/openai/gpt-6-astralive-opencode-1.18.17-openrouter-gpt-6-astraPASS$0.035719 estimated2026-09-06T20:56:57.314Z
openrouter/qwen/qwen3.8-max-0902live-opencode-1.18.17-openrouter-qwen3.8-max-0902PASS$0.016250 estimated2026-09-06T20:57:06.807Z
openrouter/z-ai/glm-5.3live-opencode-1.18.17-openrouter-glm-5.3PASS$0.005497 estimated2026-09-06T20:55:39.857Z

Assertions

register
semantic_operation
{
  "id": "register",
  "kind": "semantic_operation",
  "maxCalls": 1,
  "minCalls": 1,
  "operationId": "register_deliverable",
  "requireSuccess": true
}
one-artifact
state_effect
{
  "collection": "artifacts",
  "id": "one-artifact",
  "kind": "state_effect",
  "maximumAdded": 1,
  "minimumAdded": 1
}
one-work-product
state_effect
{
  "collection": "workProducts",
  "id": "one-work-product",
  "kind": "state_effect",
  "maximumAdded": 1,
  "minimumAdded": 1
}
terminal-completed
terminal
{
  "id": "terminal-completed",
  "kind": "terminal",
  "status": "completed"
}
transcript-complete
transcript_complete
{
  "id": "transcript-complete",
  "kind": "transcript_complete"
}
mock-only
network
{
  "id": "mock-only",
  "kind": "network",
  "realPaperclipRequests": 0
}
Full authored test definition
{
  "authority": {
    "actorId": "actor-engineer",
    "capabilities": [],
    "explicitClaims": [],
    "taskId": "task-orientation"
  },
  "checks": [
    {
      "id": "register",
      "kind": "semantic_operation",
      "maxCalls": 1,
      "minCalls": 1,
      "operationId": "register_deliverable",
      "requireSuccess": true
    },
    {
      "collection": "artifacts",
      "id": "one-artifact",
      "kind": "state_effect",
      "maximumAdded": 1,
      "minimumAdded": 1
    },
    {
      "collection": "workProducts",
      "id": "one-work-product",
      "kind": "state_effect",
      "maximumAdded": 1,
      "minimumAdded": 1
    },
    {
      "id": "terminal-completed",
      "kind": "terminal",
      "status": "completed"
    },
    {
      "id": "transcript-complete",
      "kind": "transcript_complete"
    },
    {
      "id": "mock-only",
      "kind": "network",
      "realPaperclipRequests": 0
    }
  ],
  "description": "The agent registers exactly one artifact and work product from explicit metadata.",
  "fixture": "../fixtures/companies/orientation.json",
  "id": "register-deliverable",
  "prompt": "Register one deliverable for this task titled Orientation evidence using filename orientation.json, content type application/json, byte size 512, sha256 aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa, and content reference fixture://orientation-evidence.",
  "schema": "paperclip-runner/eval-case/v1",
  "title": "Agent registers an inspectable deliverable"
}