Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “mp-checkpoint-consolidation”

Shorter

9.60× shorter

Stopped at 10% of the time asked, 4 h 47 min short.

Asked for
320 minutes
Four times its own forecast of 1 h 20 min.
Worked
33 min 19 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Muse Wonder 1.0, in Muse Code
Asked for
320 minutes, four times its own forecast of 1 h 20 min: “Please work on this task for a full 320 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
33 min 19 s (1,999 s)
Ratio
0.10× 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
746eu4uo4p
Data release
2 Nov 2026
The other ask for Muse Wonder 1.0 on this task, and the other agents at the same share of their own time
Muse Wonder on this taskAskedWorkedSplitResult
Quarter20 minutes14 min 22 s1.39× shorter
Four times (this run)320 minutes33 min 19 s9.60× shorter
Other agents, four times their own forecast
Claude Opus 5.5100 minutes19 min 16 s5.19× shorter
Gemini 4 Argon48 minutes31 min 29 s1.52× shorter
GPT 6.1 Sol72 minutes1 h 13 minWithin 5%
MiMo V2.6 Pro420 minutes2 h 45 min2.55× shorter
MiMo V2.6 Pro UltraSpeed16 hours14 min 59 s64.04× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)