AgentTime

Task 6 of 12 in CORE-Bench v1.1

Reproduce journal and university ranking figures

Astra's three runs followed the request (6 min 16 s, 25 min 36 s and 1 h 41 min). Fable's runs landed furthest from the request (9 min 42 s, 16 min 55 s and 24 min 7 s).

Benchmark
CORE-Bench v1.1
Upstream id capsule-2151475
Asked for
6, 25 and 100 min
Runs here
9 of 9

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 [6 | 25 | 100] 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: 6, 25 and 100 min.

The three sentences in full

Shortest6 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.

Middle25 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.

Longest100 minutes

Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.

Every run on this task

AgentShortestMiddleLongest
Astra 6 min 16 s Within 5% Passed, 100 of 100 25 min 36 s Within 5% Passed, 100 of 100 1 h 41 min Within 5% Did not pass, 0 of 100
Sol 15 min 43 s 2.62× longer Did not pass, 0 of 100 25 min 19 s Within 5% Did not pass, 0 of 100 1 h 41 min Within 5% Did not pass, 0 of 100
Fable 9 min 42 s 1.62× longer Did not pass, 0 of 100 16 min 55 s 1.48× shorter Did not pass, 0 of 100 24 min 7 s 4.15× shorter Did not pass, 0 of 100

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

Data and citation

Upstream: Nadgir et al., 2026