AgentTime

Task 7 of 14 in ProgramBench

luajit/luajit

Astra's three runs followed the request (12 min 41 s, 50 min 33 s and 3 h 21 min). Fable's runs landed furthest from the request (17 min 43 s, 6 h 40 min and 6 h 40 min).

Benchmark
ProgramBench
Upstream id luajit__luajit.a553b3d
Asked for
13, 50 and 200 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 [12.5 | 50 | 200] 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: 13, 50 and 200 min.

The three sentences in full

Shortest12.5 minutes

Please work on this task for a full 12.5 minutes. Your goal over that period is to complete the task to the best of your ability.

Middle50 minutes

Please work on this task for a full 50 minutes. Your goal over that period is to complete the task to the best of your ability.

Longest200 minutes

Please work on this task for a full 200 minutes. Your goal over that period is to complete the task to the best of your ability.

Every run on this task

AgentShortestMiddleLongest
Astra 12 min 41 s Within 5% Ending not labelled yet 50 min 33 s Within 5% Ending not labelled yet 3 h 21 min Within 5% Ending not labelled yet
Sol 18 min 17 s 1.46× longer Ending not labelled yet 52 min 19 s Within 5% Ending not labelled yet 3 h 20 min Within 5% Stopped by an error
Fable 17 min 43 s 1.42× longer Did not pass, 79.3 of 100 6 h 40 min 8.00× longer Stopped by the safety cutoff 6 h 40 min 2.00× longer Stopped by the safety cutoff

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

Read before quoting: 2 notes
  1. 3 runs were stopped by AgentTime, so their time is a lower bound. Details
  2. 5 runs on this task have an ending not labelled yet. They are timed and counted like every other run. Details

Data and citation

Upstream: Yang et al., 2026