Search-SWE
CPU TASK Valid result

Visual-Document Question Answering

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

Task score (%)17.8
Input Tokens17,102,874including 16,725,088 cached
Output Tokens189,670
Agent time48min
Cost$0.31
Recorded steps113

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
2026-10-25T00:08:59.986363Z
Coding finished
2026-10-25T00:57:40.182692Z
Input (includes cache)
17,102,874
Cached input (subset)
16,725,088
Cache writes (subset)
348,315
Output
189,670
Reasoning (reported separately; not added)
141,090
Recorded responses
110

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_answers_uniform_full_judge_regrade",
  "task_commit": "ddb979fcd5d562af55a3d6e0d8a2b7a961770433",
  "verifier_commit": "ddb979fcd5d562af55a3d6e0d8a2b7a961770433",
  "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
visual-document-qa-gpt-6-luna-max-6ddef3fe3d09
Source trajectory SHA-256
bd2bbe8f4baada2d6db209da2db5c74684d094dc85cfb88242c9e206d09836f3
Final reward SHA-256
02af5b7993bf1b9c30183c4871407e9318ca0b3164485c4c4f356381c8509616