BacktestBench - Ticker Selection: leaderboard
The Ticker Selection task family of BacktestBench (2026): selecting the stock a natural-language strategy would pick, from a strategy written in natural language over a database of real market records. Each model drives the same retrieval, SQL and Python-execution pipeline; the score is accuracy in percent against the executed reference backtest; higher is better.
Metric: Back-test accuracy (%) on the Ticker Selection task family (selecting the stock a natural-language strategy would pick), synthetic BacktestBench test split (the expert-crafted subset excluded), each model driving the AutoBacktest pipeline of the authors (Summarizer, SQL Retriever and Python Coder agents) over a PostgreSQL market database, temperature 0.6; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 23 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 90.37 | #145 |
| 2 | Seed 1.8 | 85.83 | #252 |
| 3 | Qwen 3 Max | 85.56 | #415 |
| 4 | Qwen 3 235B A22B 2507 (Thinking) | 82.26 | #466 |
| 5 | MiniMax-M2.1 | 81.71 | #575 |
| 6 | GLM-4.7 | 80.33 | #380 |
| 7 | DeepSeek V3.2 | 79.78 | #419 |
| 8 | Qwen 3 32B | 75.93 | #972 |
| 9 | GPT-OSS-120B | 74 | #704 |
| 10 | MiMo-V2-Flash | 73.04 | #684 |
| 11 | Qwen 3 30B A3B 2507 (Thinking) | 71.25 | #764 |
| 12 | Qwen 3 Next 80B A3B (Thinking) | 67.4 | #594 |
| 13 | Kimi K2 (Thinking) | 66.57 | |
| 14 | Qwen 3 Coder Plus | 63.41 | #720 |
| 15 | Qwen 3 14B | 62.04 | #1269 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=backtestbench-ticker-selection · How It Works · Data refreshed daily, snapshot 2026-11-21.