Time Series Reasoning on WeatherBench 2
54.7AccuracyGPT-5
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-52026.04 | 54.7 | |
| Gemini-2.5-Pro2026.04 | 45.3 | |
| gpt-4o2026.04 | 38.9 | |
| o3-mini2026.04 | 37.9 | |
| Qwen2.5-VL-Instruct2026.04 | 36.8 | |
| random guess2026.04 | 25 | |
| Gemma-3-27b-it2026.04 | 23.2 |