LexKairos - Global Event Ordering: leaderboard
Metric: Accuracy (%; 500 items: order the events of a case chronologically; 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: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (Non-reasoning) | 98.4 |
| 2 | DeepSeek R1 | 98 |
| 3 | DeepSeek V4 Flash (Non-reasoning) | 93.8 |
| 4 | Gemini 3 Flash (Minimal) | 90 |
| 5 | Qwen 3.5 9B (Non-reasoning) | 84.6 |
| 6 | Llama 3.1 8B | 44.8 |
Interactive version: theaggregate.ai/benchmark?slug=lexkairos-global-event-ordering · How It Works · Data refreshed daily, snapshot 2026-09-29.