StatABench - Nonparametric Statistics: leaderboard

Metric: Accuracy (%) on the 30 nonparametric statistics questions of Stat-Closed; Stat-Closed questions (multiple choice, fill in the blank, decision making, practical application with datasets) answered with the SAToolKit statistical functions through the LangChain MCP baseline tool-use setting, temperature 0; direct matching for closed answers and an LLM judge for open-form answers; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.586.7
2Qwen 2.5 72B Instruct73.3
3GPT-5.173.3
4Qwen 2.5 7B Instruct60
5DeepSeek V353.3
6GPT-4o Mini46.7
7Llama 3.1 8B Instruct43.3
8Qwen 2.5 32B Instruct40
9Qwen 3 8B (Non-reasoning)26.7

Interactive version: theaggregate.ai/benchmark?slug=statabench-nonparametric-statistics · How It Works · Data refreshed daily, snapshot 2026-09-29.