AgentTime

Task 1 of 14 in ProgramBench

cweill/gotests

Astra's three runs followed the request (12 min 53 s, 50 min 38 s and 3 h 21 min). Fable worked 1 h 8 min, 1 h 13 min and 1 h 20 min whatever it was asked.

Benchmark
ProgramBench
Upstream id cweill__gotests.2a672c5
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 53 s Within 5% Did not pass, 64.5 of 100 50 min 38 s Within 5% Ending not labelled yet 3 h 21 min Within 5% Ending not labelled yet
Sol 19 min 48 s 1.58× longer Did not pass, 62.7 of 100 50 min 59 s Within 5% Did not pass, 87.7 of 100 1 h 11 min 2.81× shorter Did not pass, 88.1 of 100
Fable 1 h 8 min 5.43× longer Did not pass, 0 of 100 1 h 13 min 1.46× longer Did not pass, 94.5 of 100 1 h 20 min 2.50× 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: Yang et al., 2026