Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “mp-checkpoint-consolidation”
Shorter
5.19× shorterStopped at 19% of the time asked, 1 h 21 min short.
- Asked for
- 100 minutes
- Four times its own forecast of 25 min.
- Worked
- 19 min 16 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
- 100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 19 min 16 s (1,156 s)
- Ratio
- 0.19× 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
- k7iwvknfkw
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 6.25 minutes | 2 min 11 s | 2.85× shorter | |
| Four times (this run) | 100 minutes | 19 min 16 s | 5.19× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 48 minutes | 31 min 29 s | 1.52× shorter | |
| GPT 6.1 Sol | 72 minutes | 1 h 13 min | Within 5% | |
| MiMo V2.6 Pro | 420 minutes | 2 h 45 min | 2.55× shorter | |
| MiMo V2.6 Pro UltraSpeed | 16 hours | 14 min 59 s | 64.04× shorter | |
| Muse Wonder 1.0 | 320 minutes | 33 min 19 s | 9.60× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)