Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Resolve a 20-claim heat-pump warranty exception queue”
Shorter
2.54× shorterStopped at 39% of the time asked, 1 h 25 min short.
- Asked for
- 140 minutes
- Four times its own forecast of 35 min.
- Worked
- 55 min 8 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- Benchmark
- Terminal-Bench 4.0
- Asked for
- 140 minutes, four times its own forecast of 35 min: “Please work on this task for a full 140 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 55 min 8 s (3,308 s)
- Ratio
- 0.39× 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
- 5gipmyszx6
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 8.75 minutes | 1 min 32 s | 5.72× shorter | |
| Four times (this run) | 140 minutes | 55 min 8 s | 2.54× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 60 minutes | 30 min 22 s | 1.98× 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)