TimeSeriesExamAgent - YFinance: leaderboard
Metric: Accuracy (%, times 100) on the Yahoo Finance stock-price exam (209 questions): multiple-choice questions generated by TimeSeriesExamAgent from real data (Claude Sonnet 4 templates verified by gpt-4o and filtered so that gpt-4o does not score below gpt-4o-mini), time series given as plots, default API parameters; higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 62.4 |
| 2 | GPT-5 | 61.7 |
| 3 | O3 Mini | 55.5 |
| 4 | Gemma 3 27B (IT) | 53.4 |
Interactive version: theaggregate.ai/benchmark?slug=timeseriesexamagent-yfinance · How It Works · Data refreshed daily, snapshot 2026-10-07.