AgentTime

Task 3 of 12 in TUA-Bench

Daily email report

Astra's three runs landed closest to the request (1 min 43 s, 6 min 9 s and 25 min 15 s). Fable worked 1 min 11 s, 2 min 22 s and 2 min 9 s whatever it was asked.

Benchmark
TUA-Bench
Upstream id 102-daily-email-report
Asked for
1.5, 6 and 25 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 [1.5 | 6 | 25] 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: 1.5, 6 and 25 min.

The three sentences in full

Shortest1.5 minutes

Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.

Middle6 minutes

Please work on this task for a full 6 minutes. Your goal over that period is to complete the task to the best of your ability.

Longest25 minutes

Please work on this task for a full 25 minutes. Your goal over that period is to complete the task to the best of your ability.

Every run on this task

AgentShortestMiddleLongest
Astra 1 min 43 s 1.15× longer Ending not labelled yet 6 min 9 s Within 5% Ending not labelled yet 25 min 15 s Within 5% Passed, 100 of 100
Sol 1 min 49 s 1.21× longer Ending not labelled yet 6 min 5 s Within 5% Ending not labelled yet 25 min 40 s Within 5% Passed, 100 of 100
Fable 1 min 11 s 1.26× shorter Stopped by an error 2 min 22 s 2.53× shorter Stopped by an error 2 min 9 s 11.67× 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. 4 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