paperclip-runner evalsstatic evidence
Agent discovers and reads a task document
read-task-document
The agent lists available documents before reading the eval-notes document.
Prompt
First call list_documents to inspect the documents attached to your assigned task. Then call read_document for the document with key eval-notes and summarize it. Do not change state.
Fixture
../fixtures/companies/orientation.jsonAuthority
{
"actorId": "actor-engineer",
"capabilities": [],
"explicitClaims": [],
"taskId": "task-orientation"
}Current results
| Model | Configuration | Result | Estimated cost | Run time |
|---|---|---|---|---|
| claude-sonnet-5 | live-acpx-0.13.1-claude-acp-0.70.0-sonnet-5 | PASS | $0.043688 estimated | 2026-09-06T21:22:27.673Z |
| claude-sonnet-5 | live-claude-managed-agents-2026-04-01-sonnet-5 | PASS | $0.017302 estimated | 2026-09-06T21:21:48.409Z |
| global.anthropic.claude-sonnet-4-6 | live-aws-agentcore-global-anthropic-claude-sonnet-4-6 | PASS | $0.036744 estimated | 2026-09-06T21:22:16.687Z |
| gpt-5.4-mini | live-codex-pinned | PASS | $0.001711 estimated | 2026-09-06T21:24:05.648Z |
| gpt-5.6-sol | live-acpx-0.13.1-codex-acp-1.6.2-control | Not run | — | — |
| openrouter/anthropic/claude-sonnet-5 | live-opencode-1.18.17-openrouter-claude-sonnet-5 | PASS | $0.018135 estimated | 2026-09-06T21:24:05.698Z |
| openrouter/deepseek/deepseek-v4-flash-0731 | live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731 | PASS | $0.000585 estimated | 2026-09-06T21:28:21.291Z |
| openrouter/google/gemini-3.8-flash | live-opencode-1.18.17-openrouter-gemini-3.8-flash | PASS | $0.015238 estimated | 2026-09-06T21:24:38.350Z |
| openrouter/openai/gpt-6-astra | live-opencode-1.18.17-openrouter-gpt-6-astra | PASS | $0.030158 estimated | 2026-09-06T21:26:05.442Z |
| openrouter/qwen/qwen3.8-max-0902 | live-opencode-1.18.17-openrouter-qwen3.8-max-0902 | PASS | $0.014788 estimated | 2026-09-06T21:27:20.223Z |
| openrouter/z-ai/glm-5.3 | live-opencode-1.18.17-openrouter-glm-5.3 | PASS | $0.025381 estimated | 2026-09-06T21:25:24.552Z |
Assertions
list-documents
semantic_operation
{
"id": "list-documents",
"kind": "semantic_operation",
"minCalls": 1,
"operationId": "list_documents",
"requireSuccess": true
}read-document
semantic_operation
{
"id": "read-document",
"kind": "semantic_operation",
"minCalls": 1,
"operationId": "read_document",
"requireSuccess": true
}list-before-read
operation_order
{
"after": "read_document",
"before": "list_documents",
"id": "list-before-read",
"kind": "operation_order"
}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": "list-documents",
"kind": "semantic_operation",
"minCalls": 1,
"operationId": "list_documents",
"requireSuccess": true
},
{
"id": "read-document",
"kind": "semantic_operation",
"minCalls": 1,
"operationId": "read_document",
"requireSuccess": true
},
{
"after": "read_document",
"before": "list_documents",
"id": "list-before-read",
"kind": "operation_order"
},
{
"id": "terminal-completed",
"kind": "terminal",
"status": "completed"
},
{
"id": "transcript-complete",
"kind": "transcript_complete"
},
{
"id": "mock-only",
"kind": "network",
"realPaperclipRequests": 0
}
],
"description": "The agent lists available documents before reading the eval-notes document.",
"fixture": "../fixtures/companies/orientation.json",
"id": "read-task-document",
"prompt": "First call list_documents to inspect the documents attached to your assigned task. Then call read_document for the document with key eval-notes and summarize it. Do not change state.",
"schema": "paperclip-runner/eval-case/v1",
"title": "Agent discovers and reads a task document"
}