ProgramBench, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “jesseduffield/lazygit”
Within 5%
Within 5%Worked 100% of the time asked, within 5% of it.
- Asked for
- 480 minutes
- Four times its own forecast of 2 h.
- Worked
- 8 h 1 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- ProgramBench
- Asked for
- 480 minutes, four times its own forecast of 2 h: “Please work on this task for a full 480 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 8 h 1 min (28,841 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
- etldb5xkbv
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 30 minutes | 30 min 21 s | Within 5% | |
| Four times (this run) | 480 minutes | 8 h 1 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 800 minutes | 26 h 40 min | 2.00× longer | |
| Gemini 4 Argon | 340 minutes | 1 h 3 min | 5.36× shorter | |
| MiMo V2.6 Pro | 160 hours | 2 h 6 min | 76.42× shorter | |
| MiMo V2.6 Pro UltraSpeed | 60 hours | 54 min 44 s | 65.78× shorter | |
| Muse Wonder 1.0 | 48 hours | 13 min 56 s | 206.60× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026