StatABench - Regression: leaderboard

Metric: Accuracy (%) on the 20 regression 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 4.575
2DeepSeek V375
3GPT-5.170
4Qwen 2.5 72B Instruct65
5Qwen 2.5 32B Instruct60
6Qwen 2.5 7B Instruct50
7Qwen 3 8B (Non-reasoning)50
8Llama 3.1 8B Instruct35
9GPT-4o Mini35

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