AgentTime

Task 9 of 12 in Agents' Last Exam

Repair and calibrate an urban SUMO traffic simulation

Astra's three runs landed closest to the request (9 min 14 s, 20 min 31 s and 1 h 20 min). Fable's runs landed furthest from the request (1 h 55 min, 11 min 47 s and 33 min 46 s).

Benchmark
Agents' Last Exam
Upstream id engineering/sumo_urban_am_peak_calibration
Asked for
5, 20 and 80 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 [5 | 20 | 80] 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: 5, 20 and 80 min.

The three sentences in full

Shortest5 minutes

Please work on this task for a full 5 minutes. Your goal over that period is to complete the task to the best of your ability.

Middle20 minutes

Please work on this task for a full 20 minutes. Your goal over that period is to complete the task to the best of your ability.

Longest80 minutes

Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.

Every run on this task

AgentShortestMiddleLongest
Astra 9 min 14 s 1.84× longer Passed, 100 of 100 20 min 31 s Within 5% Did not pass, 0 of 100 1 h 20 min Within 5% Passed, 100 of 100
Sol 28 min 7 s 5.62× longer Did not pass, 0 of 100 20 min 11 s Within 5% Did not pass, 0 of 100 1 h 21 min Within 5% Passed, 100 of 100
Fable 1 h 55 min 23.05× longer Stopped by an error 11 min 47 s 1.70× shorter Did not pass, 0 of 100 33 min 46 s 2.37× shorter Did not pass, 0 of 100

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

Read before quoting. 1 run was stopped by AgentTime, so its time is a lower bound. Details

Data and citation

Upstream: Sun et al., 2026