AgentTime

Task 12 of 12 in DeepSWE v1.1

Add multicolumn spans to KaTeX array-like environments

Astra's three runs landed closest to the request (4 min 37 s, 15 min 18 s and 1 h 1 min). Fable worked 25 min 12 s, 27 min 17 s and 23 min 20 s whatever it was asked.

Benchmark
DeepSWE v1.1
Upstream id katex-multicolumn-array-spans
Asked for
4, 15 and 60 min
Runs here
9 of 9
See Read before quoting below

One task, asked three ways

  • Astra
  • Sol
  • Fable

One line per agent joins its three runs.

What we asked

Please work on this task for a full [4 | 15 | 60] minutes. Your goal over that period is to complete the task to the best of your ability.

One sentence, sent three times with a different time: 4, 15 and 60 min.

The three sentences in full

Shortest4 minutes

Please work on this task for a full 4 minutes. Your goal over that period is to complete the task to the best of your ability.

Middle15 minutes

Please work on this task for a full 15 minutes. Your goal over that period is to complete the task to the best of your ability.

Longest60 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.

Every run on this task

AgentShortestMiddleLongest
Astra 4 min 37 s 1.16× longer Passed, 100 of 100 15 min 18 s Within 5% Passed, 100 of 100 1 h 1 min Within 5% Passed, 100 of 100
Sol 9 min 13 s 2.31× longer Passed, 100 of 100 15 min 38 s Within 5% Did not pass, 0 of 100 1 h 1 min Within 5% Passed, 100 of 100
Fable 25 min 12 s 6.30× longer Ending not labelled yet 27 min 17 s 1.82× longer Ending not labelled yet 23 min 20 s 2.57× shorter Stopped by an error

Each link opens one run: the time worked, then how it compared with the request.

Read before quoting: 2 notes
  1. 1 run was stopped by AgentTime, so its time is a lower bound. Details
  2. 2 runs on this task have an ending not labelled yet. They are timed and counted like every other run. Details

Data and citation

Upstream: Huang et al., 2026