AgentTime

Task 10 of 10 in Sakana ALE-Bench

AtCoder Heuristic Contest 46

Astra's three runs followed the request (10 min 8 s, 40 min 15 s and 2 h 30 min). Fable's runs landed furthest from the request (7 min 3 s, 23 min 7 s and 5 h).

Benchmark
Sakana ALE-Bench
Upstream id ahc046
Asked for
10, 40 and 150 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 [10 | 40 | 150] 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: 10, 40 and 150 min.

The three sentences in full

Shortest10 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.

Middle40 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.

Longest150 minutes

Please work on this task for a full 150 minutes. Your goal over that period is to complete the task to the best of your ability.

Every run on this task

AgentShortestMiddleLongest
Astra 10 min 8 s Within 5% Performance 3523 40 min 15 s Within 5% Performance 3523 2 h 30 min Within 5% Stopped by an error
Sol 28 min 54 s 2.89× longer Performance 116 40 min 39 s Within 5% Performance 2591 2 h 31 min Within 5% Performance 2736
Fable 7 min 3 s 1.42× shorter Ending not labelled yet 23 min 7 s 1.73× shorter Ending not labelled yet 5 h 2.00× longer Ending not labelled yet

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. 3 runs on this task have an ending not labelled yet. They are timed and counted like every other run. Details

Data and citation

Upstream: Imajuku et al., 2025