Search-SWE
CPU TASK Valid result

Scientific-Paper Question Answering

MiMo-V2.6-Flash · Codex (v0.164.0) · reasoning effort high

Task description ↗Task at evaluation revision ↗← Previous taskNext task →
Task score (%)20.0
Input Tokens16,093,014including 11,906,816 cached
Output Tokens592,360
Agent time2h 0min
Cost$0.79
Recorded steps144

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
agent_timeout
Coding started
2026-10-23T20:56:21.981785Z
Coding finished
2026-10-23T22:56:22.431995Z
Input (includes cache)
16,093,014
Cached input (subset)
11,906,816
Cache writes (subset)
0
Output
592,360
Reasoning (reported separately; not added)
5,513
Recorded responses
141

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": 7200,
  "coding_commit": null,
  "effort": "high",
  "model": "xiaomi/mimo-v2.6-flash",
  "provider": "OpenRouter",
  "resources": null,
  "run_mode": "official_harbor_regrade",
  "task_commit": null,
  "verifier_commit": "bb34e915be5c2b2948146c2d7862cb58652d6300",
  "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
Exported ATIF trajectory (.json.gz) ↓Final evaluation (.json) ↓

Public text redacts private values and normalizes host paths. Source hashes identify the original records.

Trial ID
scientific-paper-qa-mimo-v2.6-flash-high-3f2e72195a73
Source trajectory SHA-256
18d40bc327dd98ec28e896dc6d0d354cd6640e71a5b5da7febad40d5792445bf
Final reward SHA-256
e98935c4c44a75de37809840f21def21a8fdb5a3f96222cb9c5f071c6c96a6bf