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

Claude Opus 5.5 on “mp-checkpoint-consolidation”

Shorter

2.85× shorter

Stopped at 35% of the time asked, 4 min 4 s short.

Asked for
6.25 minutes
A quarter of its own forecast of 25 min.
Worked
2 min 11 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
6.25 minutes, a quarter of its own forecast of 25 min: “Please work on this task for a full 6.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 min 11 s (131 s)
Ratio
0.35× 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
3bzyqooypq
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)6.25 minutes2 min 11 s2.85× shorter
Four times100 minutes19 min 16 s5.19× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon3 minutes22 min 21 s7.45× longer
GPT 6.1 Sol4.5 minutes9 min 2 s2.01× longer
MiMo V2.6 Pro26.25 minutes58 min 7 s2.21× longer
MiMo V2.6 Pro UltraSpeed1 hour41 min 19 s1.45× shorter
Muse Wonder 1.020 minutes14 min 22 s1.39× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)