LaborLawBench: leaderboard
Metric: Mean Task Score (%; unweighted mean of 12 labor-law task scores on a 0-1 scale). Source: arxiv.org. Saturation forecast: Estimated already saturated. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3 (0324) | 61 |
| 2 | GPT-4o | 57 |
| 3 | Moonshot v1 8K | 54 |
Interactive version: theaggregate.ai/benchmark?slug=laborlawbench · How It Works · Data refreshed daily, snapshot 2026-09-25.