LexKairos (Thinking Mode) - Event Relation Discerning: leaderboard
Metric: F1 score (%; 450 items: classify the temporal relation between two events of a judicial case; 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 December 2026. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (High) | 92.8 |
| 2 | Gemini 3 Flash (High) | 88.15 |
| 3 | Qwen 3.5 9B (Thinking) | 87.67 |
| 4 | DeepSeek V4 Flash (High) | 74.14 |
Interactive version: theaggregate.ai/benchmark?slug=lexkairos-thinking-mode-event-relation-discerning · How It Works · Data refreshed daily, snapshot 2026-09-29.