Search-SWE
CPU TASK Valid result

Long-PDF Sentence Evidence

GPT-6 Luna · Codex (v0.164.0) · reasoning effort max

Task score (%)33.3
Input Tokens25,919,795including 25,580,157 cached
Output Tokens273,195
Agent time1h 22min
Cost$0.59
Recorded steps137

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
2026-10-23T22:59:22.168823Z
Coding finished
2026-10-24T00:21:47.384237Z
Input (includes cache)
25,919,795
Cached input (subset)
25,580,157
Cache writes (subset)
339,239
Output
273,195
Reasoning (reported separately; not added)
206,141
Recorded responses
133

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": null,
  "coding_commit": null,
  "effort": "max",
  "model": "openai/gpt-6-luna",
  "provider": "OpenRouter",
  "resources": null,
  "run_mode": "saved_evidence_uniform_semantic_regrade",
  "task_commit": "7e7ce5c052aa4d0cace60dc9a1c419095d521c7c",
  "verifier_commit": "7e7ce5c052aa4d0cace60dc9a1c419095d521c7c",
  "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
long-pdf-evidence-gpt-6-luna-max-96f6af4d4d99
Source trajectory SHA-256
cd9a3bdccee6355442b0cfdc6c082e6e7466cd0db8126bf835392cc46bad4760
Final reward SHA-256
60cdf1f124bbef1d1f5ab0182f44a2c71c50290915d9caa533ad82cfb0113c60