ProgramBench, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “johnkerl/miller”
Shorter
2.06× shorterStopped at 48% of the time asked, 10 h 18 min short.
- Asked for
- 20 hours
- Four times its own forecast of 5 h.
- Worked
- 9 h 42 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- Benchmark
- ProgramBench
- Task
- johnkerl/miller
- Asked for
- 20 hours, four times its own forecast of 5 h: “Please work on this task for a full 20 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 9 h 42 min (34,901 s)
- Ratio
- 0.48× 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
- kjtpc37bx3
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1.25 hours | 26 min 57 s | 2.78× shorter | |
| Four times (this run) | 20 hours | 9 h 42 min | 2.06× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 480 minutes | 1 h 47 min | 4.48× shorter | |
| GPT 6.1 Sol | 480 minutes | 8 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 40 hours | 54 min 12 s | 44.28× shorter | |
| MiMo V2.6 Pro UltraSpeed | 160 hours | 4 h 35 min | 34.90× shorter | |
| Muse Wonder 1.0 | 73.3 hours | 19 min 53 s | 221.12× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026