Time Series Reasoning on PTB-XL
51.7AccuracyGemma-3-27b-it
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemma-3-27b-it2026.04 | 51.7 | |
| Qwen2.5-VL-Instruct2026.04 | 49 | |
| o3-mini2026.04 | 47.7 | |
| Gemini-2.5-Pro2026.04 | 45.7 | |
| GPT-52026.04 | 45 | |
| gpt-4o2026.04 | 42.4 | |
| random guess2026.04 | 25 |