AgentTime

Task 11 of 12 in Agents' Last Exam

Compress a 3D Gaussian Splatting scene without losing quality

Astra's three runs landed closest to the request (6 min 39 s, 15 min 51 s and 1 h 2 min). Fable's runs landed furthest from the request (43 min 45 s, 13 min 21 s and 46 min 53 s).

Benchmark
Agents' Last Exam
Upstream id visual_media/compress_3dgs_scene_ply
Asked for
4, 15 and 60 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 [4 | 15 | 60] 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: 4, 15 and 60 min.

The three sentences in full

Shortest4 minutes

Please work on this task for a full 4 minutes. Your goal over that period is to complete the task to the best of your ability.

Middle15 minutes

Please work on this task for a full 15 minutes. Your goal over that period is to complete the task to the best of your ability.

Longest60 minutes

Please work on this task for a full 60 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 39 s 1.66× longer Did not pass, 0 of 100 15 min 51 s 1.06× longer Passed, 100 of 100 1 h 2 min Within 5% Passed, 100 of 100
Sol 10 min 55 s 2.73× longer Passed, 100 of 100 28 min 36 s 1.91× longer Passed, 100 of 100 1 h 1 min Within 5% Passed, 100 of 100
Fable 43 min 45 s 10.94× longer Passed, 100 of 100 13 min 21 s 1.12× shorter Passed, 100 of 100 46 min 53 s 1.28× shorter Passed, 100 of 100

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

Data and citation

Upstream: Sun et al., 2026