CLIR-Bench - Time-Series Summarization: leaderboard
The clinical time-series summarization task of CLIR-Bench (2026): accuracy in percent at summarizing the overall clinical status that a serialized irregular ICU trajectory reflects, 4-option multiple choice. Chance is 25; higher is better.
Metric: Accuracy (%) on clinical time-series summarization, 4-option multiple-choice questions over serialized irregular ICU time series (Full-TS input), chance 25; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 Mini | 93.33 | #389 |
| 2 | Gemini 2.5 Flash | 91.67 | #453 |
| 3 | Qwen 3.6 27B | 74 | #341 |
| 4 | Kimi K2.6 | 58.33 | #178 |
| 5 | Qwen 3.5 9B | 30 | #803 |
| 6 | DeepSeek V4 Flash | 25 | #258 |
| 7 | Qwen 3.5 4B | 24.83 | #1175 |
| 8 | Gemma 3 27B (IT) | 21.67 | #1289 |
| 9 | Gemma 4 12B (IT) | 17.67 | #693 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=clir-bench-time-series-summarization · How It Works · Data refreshed daily, snapshot 2026-11-13.