DeepSWE v1.1, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Preserve structure needed by stylesheet selectors in OXVG”
Within 5%
Within 5%Worked 100% of the time asked, within 5% of it.
- Asked for
- 152 minutes
- Four times its own forecast of 38 min.
- Worked
- 2 h 33 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- DeepSWE v1.1
- Asked for
- 152 minutes, four times its own forecast of 38 min: “Please work on this task for a full 152 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 33 min (9,161 s)
- Ratio
- 1.00× the request
- How it ended
- Ended on its own
- Grade
- Not graded
- Clock tool
- The agent could call a wall-clock tool to read the current time.
- Wording
- The paper's standard sentence, sent in AgentTime v1.1.
- Run id
- zmoaum7nbn
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 9.5 minutes | 13 min 18 s | 1.40× longer | |
| Four times (this run) | 152 minutes | 2 h 33 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 340 minutes | 4 h 29 min | 1.26× shorter | |
| Gemini 4 Argon | 180 minutes | 2 h 25 min | 1.25× shorter | |
| MiMo V2.6 Pro | 16 hours | 55 min 7 s | 17.42× shorter | |
| MiMo V2.6 Pro UltraSpeed | 20 hours | 49 min 26 s | 24.28× shorter | |
| Muse Wonder 1.0 | 460 minutes | 48 min 12 s | 9.54× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Huang et al., 2026