Backtrader-Bench (With Tools): leaderboard
Backtrader-Bench (2026) tests LLM coding agents on algorithmic-trading questions whose answers come from executing Backtrader backtests, as four-option multiple choice with chance 25 percent. Accuracy on the curated 30-question set when the agent writes and executes code, in percent; higher is better.
Metric: Accuracy (%; one pass over the curated set of 30 four-option multiple-choice questions whose answers come from executing Backtrader backtests of five trading strategies on AAPL daily data 2020-2024; the agent writes, runs and debugs Python code in an isolated sandbox through the Cursor Agent CLI before answering). Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 90 | #48 |
| 2 | Claude Opus 4.7 | 90 | #75 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=backtrader-bench-with-tools · How It Works · Data refreshed daily, snapshot 2026-11-12.