Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “Resolve a 20-claim heat-pump warranty exception queue”
Shorter
1.98× shorterStopped at 51% of the time asked, 29 min 38 s short.
- Asked for
- 60 minutes
- Four times its own forecast of 15 min.
- Worked
- 30 min 22 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- Terminal-Bench 4.0
- Asked for
- 60 minutes, four times its own forecast of 15 min: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 30 min 22 s (1,822 s)
- Ratio
- 0.51× 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
- pwfrhika35
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 3.75 minutes | 14 min 6 s | 3.76× longer | |
| Four times (this run) | 60 minutes | 30 min 22 s | 1.98× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 140 minutes | 55 min 8 s | 2.54× shorter | |
| GPT 6.1 Sol | 88 minutes | 1 h 29 min | Within 5% | |
| MiMo V2.6 Pro | 360 minutes | 45 min 2 s | 7.99× shorter | |
| MiMo V2.6 Pro UltraSpeed | 340 minutes | 8 min 59 s | 37.86× shorter | |
| Muse Wonder 1.0 | 200 minutes | 11 min 47 s | 16.98× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)