CLIR-Bench - Threshold Forecasting: leaderboard

Metric: Accuracy (%) on threshold forecasting (will a variable cross a clinical threshold in a future window), 4-option multiple-choice questions over serialized irregular ICU time series (Full-TS input), chance 25; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 15 models tracked.

Top models

#ModelScore
1DeepSeek V4 Flash38.33
2Kimi K2.636.67
3GPT-5.4 Mini33.33
4Gemma 3 27B (IT)31.67
5Gemma 4 12B (IT)22.17
6Gemini 2.5 Flash20
7Qwen 3.5 9B18.33
8Qwen 3.5 4B18.17
9Qwen 3.6 27B10.5

Interactive version: theaggregate.ai/benchmark?slug=clir-bench-threshold-forecasting · How It Works · Data refreshed daily, snapshot 2026-09-29.