Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast

Claude Opus 5.5 on “Repair a React lead form and its auditable CRM submission pipeline”

Longer

1.10× longer

Worked 10% past the request, 1 min 8 s over.

Asked for
11.25 minutes
A quarter of its own forecast of 45 min.
Worked
12 min 23 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Asked for
11.25 minutes, a quarter of its own forecast of 45 min: “Please work on this task for a full 11.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
12 min 23 s (743 s)
Ratio
1.10× 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
3wtl54vjjr
Data release
2 Nov 2026
The other ask for Claude Opus 5.5 on this task, and the other agents at the same share of their own time
Opus 5.5 on this taskAskedWorkedSplitResult
Quarter (this run)11.25 minutes12 min 23 s1.10× longer
Four times180 minutes1 h 29 min2.02× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon4.5 minutes14 min 56 s3.32× longer
GPT 6.1 Sol7.5 minutes7 min 44 sWithin 5%
MiMo V2.6 Pro52.5 minutes29 min 7 s1.80× shorter
MiMo V2.6 Pro UltraSpeed1 hour8 min 32 s7.03× shorter
Muse Wonder 1.021.25 minutes4 min 56 s4.30× shorter

See it on the chart. Transcripts are not published yet.

Data and citation

Upstream: Merrill et al., 2026 (ICLR)