DeepSWE v1.1, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “tomlkit-toml-table-converters”
Shorter
1.07× shorterStopped at 93% of the time asked, 4 min 53 s short.
- Asked for
- 72 minutes
- Four times its own forecast of 18 min.
- Worked
- 1 h 7 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- DeepSWE v1.1
- Asked for
- 72 minutes, four times its own forecast of 18 min: “Please work on this task for a full 72 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 7 min (4,027 s)
- Ratio
- 0.93× 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
- d5br6epvsc
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 4.5 minutes | 20 min 48 s | 4.62× longer | |
| Four times (this run) | 72 minutes | 1 h 7 min | 1.07× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 160 minutes | 2 h 22 min | 1.13× shorter | |
| GPT 6.1 Sol | 128 minutes | 2 h 9 min | Within 5% | |
| MiMo V2.6 Pro | 480 minutes | 35 min 55 s | 13.37× shorter | |
| MiMo V2.6 Pro UltraSpeed | 540 minutes | 11 min 14 s | 48.04× shorter | |
| Muse Wonder 1.0 | 600 minutes | 18 min 52 s | 31.80× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Huang et al., 2026