BacktestBench - Parameter Confirmation: leaderboard

The Parameter Confirmation task family of BacktestBench (2026): selecting the candidate strategy parameter that yields the best performance indicator, 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 Parameter Confirmation task family (selecting the candidate strategy parameter that yields the best performance indicator), 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

#ModelScoreOverall rank
1Gemini 3 Pro82.46#145
2Qwen 3 Max82.28#415
3GLM-4.777.24#380
4Seed 1.877.05#252
5Qwen 3 235B A22B 2507 (Thinking)75.93#466
6DeepSeek V3.273.51#419
7Qwen 3 Coder Plus71.08#720
8GPT-OSS-120B70.34#704
9Qwen 3 32B70.34#972
10MiniMax-M2.169.22#575
11Qwen 3 Next 80B A3B (Thinking)65.86#594
12Qwen 3 30B A3B 2507 (Thinking)65.86#764
13MiMo-V2-Flash64.37#684
14Qwen 3 14B61.57#1269
15Kimi K2 (Thinking)58.02

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=backtestbench-parameter-confirmation · How It Works · Data refreshed daily, snapshot 2026-11-21.