AgentTime

Task 3 of 10 in PPTArena

Swimlane process diagram

Astra's three runs landed closest to the request (1 min 44 s, 6 min 20 s and 25 min 14 s). Fable worked 11 min 31 s, 8 min 53 s and 15 min 52 s whatever it was asked.

Benchmark
PPTArena
Upstream id 68
Asked for
1.5, 6 and 25 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 [1.5 | 6 | 25] 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: 1.5, 6 and 25 min.

The three sentences in full

Shortest1.5 minutes

Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.

Middle6 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.

Longest25 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.

Every run on this task

AgentShortestMiddleLongest
Astra 1 min 44 s 1.16× longer Score 70 of 100 6 min 20 s 1.05× longer Score 70 of 100 25 min 14 s Within 5% Score 80 of 100
Sol 4 min 3 s 2.70× longer Score 40 of 100 6 min 17 s Within 5% Score 50 of 100 26 min 45 s 1.07× longer Score 90 of 100
Fable 11 min 31 s 7.67× longer Score 0 of 100 8 min 53 s 1.48× longer Score 80 of 100 15 min 52 s 1.58× shorter Score 80 of 100

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

Data and citation