LexKairos - Temporal Distance Calculation: leaderboard
Metric: Accuracy (%; 550 items: compute the time elapsed between two case events; 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 | DeepSeek R1 | 98.73 |
| 2 | GPT-5.4 (Non-reasoning) | 98.18 |
| 3 | DeepSeek V4 Flash (Non-reasoning) | 78 |
| 4 | Gemini 3 Flash (Minimal) | 71.82 |
| 5 | Qwen 3.5 9B (Non-reasoning) | 34.73 |
| 6 | Llama 3.1 8B | 23.45 |
Interactive version: theaggregate.ai/benchmark?slug=lexkairos-temporal-distance-calculation · How It Works · Data refreshed daily, snapshot 2026-09-29.