OSWorld 2.0, middle of three requests

Claude Fable 5.1 on “Twenty recurring meetings”

Longer

1.75× longer

Worked 75% past the request, 44 min 57 s over.

Asked for
60 minutes
Worked
1 h 45 min
Grade
Did not pass
Score 68.8 of 100. Graded during the run.
How it ended
Ended on its own
Every detail of this run
Agent
Claude Fable 5.1, in Claude Code
Benchmark
OSWorld 2.0
Asked for
60 minutes: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 45 min (6,297 s)
Ratio
1.75× the request
How it ended
Ended on its own
Grade
Did not pass
It did not meet every checkpoint. The grader returned 0.688. Pass rule: Binary completion: a score of 1.00, with every checkpoint met.
Score
68.8 of 100
Graded during the run. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
pesslpyl7u
Data release
26 Sep 2026
The other requests for Claude Fable 5.1 on this task, and the other agents at this request
Fable on this taskAskedWorkedSplitResult
Shortest15 minutes1 h 42 min6.78× longer
Middle (this run)60 minutes1 h 45 min1.75× longer
Longest250 minutes51 min 49 s4.82× shorter
Other agents, middle request
GPT 6 Astra60 minutes1 h 3 minWithin 5%
GPT 5.6 Sol60 minutes1 h 40 min1.66× longer

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

Data and citation

Upstream: Yuan et al., 2026