GPU TASK Valid result
Sketch-and-Text Image Search
GPT-6 Luna · Codex · reasoning effort max
Task score (%)3.5
Input Tokens21,040,279including 20,783,360 cached
Output Tokens157,333
Agent time1h 24min
Cost$0.32
Recorded steps140
Cost is estimated from recorded agent tokens at official API rates in USD (2026-11-01; DeepSeek off-peak pricing).
Loading trajectory…
Select this tab to browse the saved files.
Coding time & token usage
- Original agent completion
- normal
- Coding started
- 2026-10-25T10:47:57.263235Z
- Coding finished
- 2026-10-25T12:11:59.020394Z
- Input (includes cache)
- 21,040,279
- Cached input (subset)
- 20,783,360
- Cache writes (subset)
- 256,508
- Output
- 157,333
- Reasoning (reported separately; not added)
- 102,468
- Recorded responses
- 137
Input includes cached input; output is counted once. Auxiliary reasoning counts are shown as recorded. Regrading does not repeat coding usage.
Select this tab to browse the saved files.
Configuration
Evaluation settings summary
{
"agent": "Codex",
"agent_timeout_sec": 21600.0,
"coding_commit": null,
"effort": "max",
"model": "openai/gpt-6-luna",
"provider": "OpenRouter",
"resources": {
"cpus": 8,
"gpus": 1,
"memory_mb": 32768,
"storage_mb": 102400
},
"run_mode": "official_harbor_full",
"task_commit": "052045836520335c1caa5e4a06ed887faacef55f",
"verifier_commit": "052045836520335c1caa5e4a06ed887faacef55f",
"version": "0.164.0"
}Select this tab to browse the saved files.
Resolved configuration
Select this tab to browse the saved files.
Trial log
Select this tab to browse the saved files.
Exceptions
Select this tab to browse the saved files.
Select this tab to browse the saved files.
Trajectory downloads & provenance
Public text redacts private values and normalizes host paths. Source hashes identify the original records.
- Trial ID
sketch-text-search-gpt-6-luna-max-d258a9625558- Source trajectory SHA-256
a28ff24b0939b4fc1c82ee58612b3d59b7e32aafc6deef254d95c5cd9ecd234b- Final reward SHA-256
90b657adc6b7aa553d9f8d6fd4a8134a93480a577b5dc140d35df86a7cdaf34f