TUA-Bench, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Daily email report”
Within 5%
Within 5%Worked 102% of the time asked, within 5% of it.
- Asked for
- 720 seconds
- Four times its own forecast of 3 min.
- Worked
- 12 min 12 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- TUA-Bench
- Asked for
- 720 seconds, four times its own forecast of 3 min: “Please work on this task for a full 720 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 12 min 12 s (732 s)
- Ratio
- 1.02× 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
- h7zri3j3se
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 45 seconds | 56 s | 1.25× longer | |
| Four times (this run) | 720 seconds | 12 min 12 s | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 20 minutes | 3 min 57 s | 5.06× shorter | |
| Gemini 4 Argon | 600 seconds | 10 min 25 s | Within 5% | |
| MiMo V2.6 Pro | 140 minutes | 6 min 31 s | 21.47× shorter | |
| MiMo V2.6 Pro UltraSpeed | 88 minutes | 2 min 51 s | 30.88× shorter | |
| Muse Wonder 1.0 | 40 minutes | 47 s | 51.28× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Chen et al., 2026