ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “dandavison/delta”
Shorter
3.86× shorterStopped at 26% of the time asked, 31 min 30 s short.
- Asked for
- 42.5 minutes
- A quarter of its own forecast of 2 h 50 min.
- Worked
- 11 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
- dandavison/delta
- Asked for
- 42.5 minutes, a quarter of its own forecast of 2 h 50 min: “Please work on this task for a full 42.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 11 min (660 s)
- Ratio
- 0.26× 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
- bcwoizii5x
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 42.5 minutes | 11 min | 3.86× shorter | |
| Four times | 680 minutes | 10 h 24 min | 1.09× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 22.5 minutes | 1 h 9 min | 3.07× longer | |
| GPT 6.1 Sol | 30 minutes | 30 min 35 s | Within 5% | |
| MiMo V2.6 Pro | 2 hours | 1 h 34 min | 1.28× shorter | |
| MiMo V2.6 Pro UltraSpeed | 11.25 hours | 2 h 19 min | 4.84× shorter | |
| Muse Wonder 1.0 | 4 hours | 15 min 27 s | 15.53× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026