Search-SWE
CPU TASK Valid result

Financial-Report Evidence Retrieval

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

Task score (%)10.6
Input Tokens14,524,405including 14,286,415 cached
Output Tokens171,722
Agent time54min
Cost$0.26
Recorded steps89

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
2026-10-24T07:21:46.376261Z
Coding finished
2026-10-24T08:16:20.802935Z
Input (includes cache)
14,524,405
Cached input (subset)
14,286,415
Cache writes (subset)
237,732
Output
171,722
Reasoning (reported separately; not added)
133,170
Recorded responses
86

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_outputs_production_rescore",
  "task_commit": "1d73c6f9c4a90ba922b7572d9395a6f40661bbb2",
  "verifier_commit": "1d73c6f9c4a90ba922b7572d9395a6f40661bbb2",
  "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
financial-report-qa-gpt-6-luna-max-162369422f12
Source trajectory SHA-256
f0b25e524efde8210ff7ba07ba630cc6c4c670dd6c39accc7da4024d1a630ee7
Final reward SHA-256
a5ab20c3d94c4f460e854a2ab7c50ae843090e85e740b8e29c20d2839b138d54