LexKairos (Thinking Mode) - Action Limitation Reasoning: leaderboard
Metric: F1 score (%; 109 items: decide whether a limitation period for an action has expired; thinking mode, built-in reasoning enabled at high effort with the vanilla prompt; temperature 0, 8,000 output tokens). Source: arxiv.org. Saturation forecast: Around January 2028. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (High) | 73.78 |
| 2 | GPT-5.4 (High) | 70.02 |
| 3 | Qwen 3.5 9B (Thinking) | 69.43 |
| 4 | DeepSeek V4 Flash (High) | 64.54 |
Interactive version: theaggregate.ai/benchmark?slug=lexkairos-thinking-mode-action-limitation-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.