Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast
GPT 6.1 Sol on “Train a lake-temperature profile model from sparse observations”
Within 5%
Within 5%Worked 103% of the time asked, within 5% of it.
- Asked for
- 11.25 minutes
- A quarter of its own forecast of 45 min.
- Worked
- 11 min 38 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- Terminal-Bench 4.0
- Asked for
- 11.25 minutes, a quarter of its own forecast of 45 min: “Please work on this task for a full 11.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 11 min 38 s (698 s)
- Ratio
- 1.03× 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
- clspplsma4
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 11.25 minutes | 11 min 38 s | Within 5% | |
| Four times | 180 minutes | 3 h 1 min | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 12.5 minutes | 10 min 35 s | 1.18× shorter | |
| Gemini 4 Argon | 5 minutes | 18 min 8 s | 3.63× longer | |
| MiMo V2.6 Pro | 45 minutes | 1 h 13 min | 1.63× longer | |
| MiMo V2.6 Pro UltraSpeed | 17.5 minutes | 25 min 19 s | 1.45× longer | |
| Muse Wonder 1.0 | 23.75 minutes | 31 min 59 s | 1.35× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)