LexKairos - Effective Status Verification: leaderboard

Metric: Accuracy (%; 480 items: classify whether a statute is in force at a given date; 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

#ModelScore
1DeepSeek R192.92
2GPT-5.4 (Non-reasoning)66.88
3Gemini 3 Flash (Minimal)64.17
4DeepSeek V4 Flash (Non-reasoning)60.83
5Llama 3.1 8B53.54
6Qwen 3.5 9B (Non-reasoning)49.17

Interactive version: theaggregate.ai/benchmark?slug=lexkairos-effective-status-verification · How It Works · Data refreshed daily, snapshot 2026-09-29.