Backtrader-Bench - Mined Questions (No Tools): leaderboard

Metric: Accuracy (%; one run on the 38 four-option questions mined by a GPT-5.5 generator with executable verification and kept only when a tool-free GPT-5.4 solver failed and a tool-using solver succeeded; answered through the Cursor SDK with every tool disabled; chance 25%). Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)60.5
2GPT-5.560.5
3Claude Opus 4.657.9
4Claude Opus 4.752.6
5Claude Sonnet 4.639.5
6GPT-5.3 Codex34.2
7Gemini 2.5 Flash29
8Grok 4.321.1
9Kimi K2.515.8

Interactive version: theaggregate.ai/benchmark?slug=backtrader-bench-mined-questions-no-tools · How It Works · Data refreshed daily, snapshot 2026-09-26.