LexKairos - Effective Version Identification: leaderboard
The Effective Version Identification sub-task of LexKairos (Tsinghua University, 2026): name the statute version in force at a given date. Accuracy in percent over 452 items in the vanilla setting (direct answer); higher is better.
Metric: Accuracy (%; 452 items: generate the statute title and version tag 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 February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (Non-reasoning) | 59.96 | #123 (GPT-5.4) |
| 2 | Gemini 3 Flash (Minimal) | 59.51 | #164 (Gemini 3 Flash) |
| 3 | DeepSeek R1 | 47.57 | #473 |
| 4 | DeepSeek V4 Flash (Non-reasoning) | 45.58 | #258 (DeepSeek V4 Flash) |
| 5 | Qwen 3.5 9B (Non-reasoning) | 40.04 | #803 (Qwen 3.5 9B) |
| 6 | Llama 3.1 8B | 12.83 | #4861 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=lexkairos-effective-version-identification · How It Works · Data refreshed daily, snapshot 2026-11-13.