Time Series Reasoning on MIT-BIH
61.4AccuracyGemini-2.5-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-2.5-Pro2026.04 | 61.4 | |
| GPT-52026.04 | 53.3 | |
| Gemma-3-27b-it2026.04 | 49.7 | |
| o3-mini2026.04 | 44.2 | |
| gpt-4o2026.04 | 41.6 | |
| Qwen2.5-VL-Instruct2026.04 | 41.1 | |
| random guess2026.04 | 25 |