AgentTime

Task 12 of 12 in TUA-Bench

Extract presenter photos

Astra's three runs landed closest to the request (2 min 51 s, 10 min 38 s and 40 min 46 s). Fable worked 2 min 38 s, 4 min 30 s and 5 min 7 s whatever it was asked.

Benchmark
TUA-Bench
Upstream id 088-extract-presenter-photos
Asked for
2.5, 10 and 40 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 [2.5 | 10 | 40] 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: 2.5, 10 and 40 min.

The three sentences in full

Shortest2.5 minutes

Please work on this task for a full 2.5 minutes. Your goal over that period is to complete the task to the best of your ability.

Middle10 minutes

Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.

Longest40 minutes

Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.

Every run on this task

AgentShortestMiddleLongest
Astra 2 min 51 s 1.14× longer Ending not labelled yet 10 min 38 s 1.06× longer Passed, 100 of 100 40 min 46 s Within 5% Stopped by an error
Sol 2 min 47 s 1.11× longer Ending not labelled yet 10 min 54 s 1.09× longer Passed, 100 of 100 41 min 33 s Within 5% Passed, 100 of 100
Fable 2 min 38 s Within 5% Stopped by an error 4 min 30 s 2.22× shorter Passed, 100 of 100 5 min 7 s 7.81× shorter Passed, 100 of 100

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

Read before quoting: 2 notes
  1. 2 runs were stopped by AgentTime, so their 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: Chen et al., 2026