ProgramBench, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “doxygen/doxygen”
Shorter
1.07× shorterStopped at 93% of the time asked, 1 h 6 min short.
- Asked for
- 16 hours
- Four times its own forecast of 4 h.
- Worked
- 14 h 54 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
- doxygen/doxygen
- Asked for
- 16 hours, four times its own forecast of 4 h: “Please work on this task for a full 16 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 14 h 54 min (53,638 s)
- Ratio
- 0.93× 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
- 7bfe5tho5h
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1 hour | 21 min 43 s | 2.76× shorter | |
| Four times (this run) | 16 hours | 14 h 54 min | 1.07× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 420 minutes | 2 h 21 min | 2.98× shorter | |
| GPT 6.1 Sol | 420 minutes | 7 h | Within 5% | |
| MiMo V2.6 Pro | 200 hours | 1 h 10 min | 172.34× shorter | |
| MiMo V2.6 Pro UltraSpeed | 60 hours | 1 h 14 min | 48.89× shorter | |
| Muse Wonder 1.0 | 72 hours | 2 h 12 min | 32.63× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026