Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast
GPT 6.1 Sol on “Resolve a 20-claim heat-pump warranty exception queue”
Longer
1.08× longerWorked 8% past the request, 28 s over.
- Asked for
- 5.5 minutes
- A quarter of its own forecast of 22 min.
- Worked
- 5 min 58 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
- 5.5 minutes, a quarter of its own forecast of 22 min: “Please work on this task for a full 5.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 5 min 58 s (358 s)
- Ratio
- 1.08× 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
- paynauubjt
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 5.5 minutes | 5 min 58 s | 1.08× longer | |
| Four times | 88 minutes | 1 h 29 min | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 8.75 minutes | 1 min 32 s | 5.72× shorter | |
| Gemini 4 Argon | 3.75 minutes | 14 min 6 s | 3.76× longer | |
| MiMo V2.6 Pro | 22.5 minutes | 17 min 14 s | 1.31× shorter | |
| MiMo V2.6 Pro UltraSpeed | 21.25 minutes | 9 min 7 s | 2.33× shorter | |
| Muse Wonder 1.0 | 12.5 minutes | 4 min 23 s | 2.85× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)