StatABench: leaderboard
Statistical analysis is a broad, complex field requiring both domain knowledge and tool proficiency. While prior work has evaluated large language models (LLMs) in this domain, existing benchmarks remain limited in scope and format. To bridge this gap, we introduce StatABench (Statistical AnalysisBenchmark), a benchmark designed to systematically assess LLMs' statistical analysis capabilities. Sta
Metric: Total (self-reported). Source: benchmarklist.com. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 | 68.6 | #135 |
| 2 | Qwen 2.5 72B | 60.6 | #499 |
| 3 | DeepSeek V3 | 57.4 | #321 |
| 4 | Qwen 2.5 32B | 51.7 | #546 |
| 5 | GPT-4o Mini | 43.3 | #599 |
| 6 | Qwen 3 8B | 39.6 | #674 |
| 7 | Qwen 2.5 7B | 38.1 | #922 |
| 8 | Llama 3.1 8B | 25.5 | #1151 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=statabench · How It Works · Data refreshed daily, snapshot 2026-10-20.