Time Series Reasoning on MIMIC-IV Waveform
43.9AccuracyQwen2.5-VL-Instruct
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-Instruct2026.04 | 43.9 | |
| GPT-52026.04 | 42.4 | |
| Gemini-2.5-Pro2026.04 | 40 | |
| gpt-4o2026.04 | 38.5 | |
| Gemma-3-27b-it2026.04 | 37 | |
| o3-mini2026.04 | 35.6 | |
| random guess2026.04 | 25 |