LabOSBench - Activation & Alignment: leaderboard
Metric: Subtask Success Rate (%; mean over the category's operation-level subtasks, 2 runs each). Source: arxiv.org. Saturation forecast: Around 2031. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed-1.6 | 59.1 |
| 2 | GPT-5.5 | 50 |
| 3 | Claude Sonnet 4.5 | 45.5 |
| 4 | Kimi K2.5 | 45.5 |
| 5 | Claude Opus 4.5 | 40.9 |
| 6 | uitars-1.5-7B | 40.9 |
Interactive version: theaggregate.ai/benchmark?slug=labosbench-activation-alignment · How It Works · Data refreshed daily, snapshot 2026-09-25.