Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Repair a React lead form and its auditable CRM submission pipeline”
Within 5%
Within 5%Worked 100% of the time asked, within 5% of it.
- Asked for
- 120 minutes
- Four times its own forecast of 30 min.
- Worked
- 2 h 1 min
- 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
- 120 minutes, four times its own forecast of 30 min: “Please work on this task for a full 120 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 1 min (7,232 s)
- Ratio
- 1.00× 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
- oarhb7mp6p
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7.5 minutes | 7 min 44 s | Within 5% | |
| Four times (this run) | 120 minutes | 2 h 1 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 180 minutes | 1 h 29 min | 2.02× shorter | |
| Gemini 4 Argon | 72 minutes | 28 min 50 s | 2.50× shorter | |
| MiMo V2.6 Pro | 840 minutes | 37 min 21 s | 22.49× shorter | |
| MiMo V2.6 Pro UltraSpeed | 16 hours | 16 min 3 s | 59.81× shorter | |
| Muse Wonder 1.0 | 340 minutes | 9 min 59 s | 34.03× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)