Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “Make a Kafka payments worker recover quickly without losing notifications”
Shorter
1.45× shorterStopped at 69% of the time asked, 24 min 38 s short.
- Asked for
- 80 minutes
- Four times its own forecast of 20 min.
- Worked
- 55 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
- 80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 55 min 22 s (3,322 s)
- Ratio
- 0.69× 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
- 45ait45ftr
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 5 minutes | 45 min 16 s | 9.05× longer | |
| Four times (this run) | 80 minutes | 55 min 22 s | 1.45× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 160 minutes | 1 h 50 min | 1.45× shorter | |
| GPT 6.1 Sol | 120 minutes | 2 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 340 minutes | 52 min 7 s | 6.52× shorter | |
| MiMo V2.6 Pro UltraSpeed | 700 minutes | 36 min 33 s | 19.15× shorter | |
| Muse Wonder 1.0 | 340 minutes | 44 min 29 s | 7.64× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)