TUA-Bench, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “Author homepage bookmarks”
Shorter
1.30× shorterStopped at 77% of the time asked, 21 s short.
- Asked for
- 1.5 minutes
- A quarter of its own forecast of 6 min.
- Worked
- 1 min 9 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- Benchmark
- TUA-Bench
- Asked for
- 1.5 minutes, a quarter of its own forecast of 6 min: “Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 9 s (69 s)
- Ratio
- 0.77× 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
- ygxem2l6rb
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1.5 minutes | 1 min 9 s | 1.30× shorter | |
| Four times | 24 minutes | 9 min 37 s | 2.49× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 37.5 seconds | 4 min 4 s | 6.50× longer | |
| GPT 6.1 Sol | 2 minutes | 2 min 15 s | 1.13× longer | |
| MiMo V2.6 Pro | 6 minutes | 12 min 8 s | 2.02× longer | |
| MiMo V2.6 Pro UltraSpeed | 7.5 minutes | 7 min 40 s | Within 5% | |
| Muse Wonder 1.0 | 5.5 minutes | 5 min 11 s | 1.06× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Chen et al., 2026