BacktestBench - Strategy Selection: leaderboard
The Strategy Selection task family of BacktestBench (2026): choosing which candidate strategy achieves the best performance under the same market conditions, 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 Strategy Selection task family (choosing which candidate strategy achieves the best performance under the same market conditions), 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 | 89.07 | #145 |
| 2 | Qwen 3 Max | 85.27 | #415 |
| 3 | Qwen 3 235B A22B 2507 (Thinking) | 85.04 | #466 |
| 4 | Seed 1.8 | 84.8 | #252 |
| 5 | DeepSeek V3.2 | 81.47 | #419 |
| 6 | GLM-4.7 | 80.76 | #380 |
| 7 | Qwen 3 Coder Plus | 77.91 | #720 |
| 8 | MiniMax-M2.1 | 76.72 | #575 |
| 9 | GPT-OSS-120B | 76.48 | #704 |
| 10 | Qwen 3 30B A3B 2507 (Thinking) | 75.06 | #764 |
| 11 | Qwen 3 32B | 72.21 | #972 |
| 12 | MiMo-V2-Flash | 71.26 | #684 |
| 13 | Qwen 3 Next 80B A3B (Thinking) | 68.17 | #594 |
| 14 | Kimi K2 (Thinking) | 67.46 | |
| 15 | Qwen 3 14B | 64.61 | #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-strategy-selection · How It Works · Data refreshed daily, snapshot 2026-11-21.