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× shorter

Stopped 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
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
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
Quarter8.75 minutes1 min 32 s5.72× shorter
Four times (this run)140 minutes55 min 8 s2.54× shorter
Other agents, four times their own forecast
Gemini 4 Argon60 minutes30 min 22 s1.98× shorter
GPT 6.1 Sol88 minutes1 h 29 minWithin 5%
MiMo V2.6 Pro360 minutes45 min 2 s7.99× shorter
MiMo V2.6 Pro UltraSpeed340 minutes8 min 59 s37.86× shorter
Muse Wonder 1.0200 minutes11 min 47 s16.98× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)