Time Series Reasoning on YFinance
62.4AccuracyGemini-2.5-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.5-Pro2026.04 | 62.4 | |
| GPT-52026.04 | 61.7 | |
| gpt-4o2026.04 | 58.6 | |
| Qwen2.5-VL-Instruct2026.04 | 57.2 | |
| o3-mini2026.04 | 55.5 | |
| Gemma-3-27b-it2026.04 | 53.4 | |
| random guess2026.04 | 25 |