ProgramBench, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “tomarrell/wrapcheck”
Shorter
2.14× shorterStopped at 47% of the time asked, 2 h 40 min short.
- Asked for
- 300 minutes
- Four times its own forecast of 1 h 15 min.
- Worked
- 2 h 20 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
- Asked for
- 300 minutes, four times its own forecast of 1 h 15 min: “Please work on this task for a full 300 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 20 min (8,398 s)
- Ratio
- 0.47× 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
- 73pt3w3gbk
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 18.75 minutes | 5 min 4 s | 3.71× shorter | |
| Four times (this run) | 300 minutes | 2 h 20 min | 2.14× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 168 minutes | 3 min 24 s | 49.41× shorter | |
| GPT 6.1 Sol | 240 minutes | 4 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 24 hours | 1 h 26 min | 16.66× shorter | |
| MiMo V2.6 Pro UltraSpeed | 28 hours | 53 min 27 s | 31.43× shorter | |
| Muse Wonder 1.0 | 20 hours | 9 min 50 s | 122.08× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026