paperclip-runner evalsstatic evidence
Agent finishes its assigned task
finish-task
The agent durably finishes the active task with a summary.
Prompt
Finish your assigned task now with the summary: Orientation eval implementation is complete.
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 | $0.132337 estimated | 2026-09-06T21:22:13.310Z |
| claude-sonnet-5 | live-claude-managed-agents-2026-04-01-sonnet-5 | PASS | $0.009932 estimated | 2026-09-06T21:22:14.777Z |
| global.anthropic.claude-sonnet-4-6 | live-aws-agentcore-global-anthropic-claude-sonnet-4-6 | PASS | $0.036996 estimated | 2026-09-06T21:22:27.293Z |
| gpt-5.4-mini | live-codex-pinned | PASS | $0.001204 estimated | 2026-09-06T21:24:04.999Z |
| gpt-5.6-sol | live-acpx-0.13.1-codex-acp-1.6.2-control | PASS | $0.007772 estimated | 2026-09-06T21:22:22.029Z |
| openrouter/anthropic/claude-sonnet-5 | live-opencode-1.18.17-openrouter-claude-sonnet-5 | PASS | $0.019350 estimated | 2026-09-06T21:24:24.552Z |
| openrouter/deepseek/deepseek-v4-flash-0731 | live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731 | PASS | $0.000649 estimated | 2026-09-06T21:28:54.131Z |
| openrouter/google/gemini-3.8-flash | live-opencode-1.18.17-openrouter-gemini-3.8-flash | PASS | $0.011867 estimated | 2026-09-06T21:24:49.296Z |
| openrouter/openai/gpt-6-astra | live-opencode-1.18.17-openrouter-gpt-6-astra | PASS | $0.028710 estimated | 2026-09-06T21:26:13.441Z |
| openrouter/qwen/qwen3.8-max-0902 | live-opencode-1.18.17-openrouter-qwen3.8-max-0902 | PASS | $0.018940 estimated | 2026-09-06T21:27:20.662Z |
| openrouter/z-ai/glm-5.3 | live-opencode-1.18.17-openrouter-glm-5.3 | PASS | $0.007812 estimated | 2026-09-06T21:25:26.918Z |
Assertions
finish
semantic_operation
{
"id": "finish",
"kind": "semantic_operation",
"maxCalls": 1,
"minCalls": 1,
"operationId": "finish_task",
"requireSuccess": true
}task-done
state_record_field
{
"collection": "tasks",
"equals": "done",
"field": "status",
"id": "task-done",
"kind": "state_record_field",
"recordId": "task-orientation"
}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": "finish",
"kind": "semantic_operation",
"maxCalls": 1,
"minCalls": 1,
"operationId": "finish_task",
"requireSuccess": true
},
{
"collection": "tasks",
"equals": "done",
"field": "status",
"id": "task-done",
"kind": "state_record_field",
"recordId": "task-orientation"
},
{
"id": "terminal-completed",
"kind": "terminal",
"status": "completed"
},
{
"id": "transcript-complete",
"kind": "transcript_complete"
},
{
"id": "mock-only",
"kind": "network",
"realPaperclipRequests": 0
}
],
"description": "The agent durably finishes the active task with a summary.",
"fixture": "../fixtures/companies/orientation.json",
"id": "finish-task",
"prompt": "Finish your assigned task now with the summary: Orientation eval implementation is complete.",
"schema": "paperclip-runner/eval-case/v1",
"title": "Agent finishes its assigned task"
}