LexKairos - Event Relation Discerning: leaderboard
Metric: F1 score (%; 450 items: classify the temporal relation between two events of a judicial case; vanilla setting, the model answers directly without extra reasoning steps (thinking disabled where the model allows it); temperature 0, 8,000 output tokens). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (Non-reasoning) | 90.58 |
| 2 | DeepSeek R1 | 87.37 |
| 3 | Gemini 3 Flash (Minimal) | 82.53 |
| 4 | Qwen 3.5 9B (Non-reasoning) | 69.94 |
| 5 | DeepSeek V4 Flash (Non-reasoning) | 54.13 |
| 6 | Llama 3.1 8B | 28.04 |
Interactive version: theaggregate.ai/benchmark?slug=lexkairos-event-relation-discerning · How It Works · Data refreshed daily, snapshot 2026-09-29.