LabOSBench - Post-processing & Completion: leaderboard

Metric: Subtask Success Rate (%; mean over the category's operation-level subtasks, 2 runs each). Source: arxiv.org. Saturation forecast: Around March 2028. 9 models tracked.

Top models

#ModelScore
1Seed-1.681.2
2GPT-5.575
3uitars-1.5-7B71.9
4Claude Sonnet 4.568.8
5Kimi K2.562.5
6Claude Opus 4.562.5

Interactive version: theaggregate.ai/benchmark?slug=labosbench-post-processing-completion · How It Works · Data refreshed daily, snapshot 2026-09-25.