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

Claude Opus 5.5 on “hof-topology-interpenetration”

Shorter

1.64× shorter

Stopped at 61% of the time asked, 4 min 52 s short.

Asked for
12.5 minutes
A quarter of its own forecast of 50 min.
Worked
7 min 38 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
12.5 minutes, a quarter of its own forecast of 50 min: “Please work on this task for a full 12.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 min 38 s (458 s)
Ratio
0.61× 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
n4meazi3bm
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)12.5 minutes7 min 38 s1.64× shorter
Four times200 minutes24 min 25 s8.19× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon7 minutes19 min 49 s2.83× longer
GPT 6.1 Sol15 minutes15 min 20 sWithin 5%
MiMo V2.6 Pro1.125 hours50 min 55 s1.33× shorter
MiMo V2.6 Pro UltraSpeed1.75 hours31 min 48 s3.30× shorter
Muse Wonder 1.047.5 minutes15 min 28 s3.07× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)