StatABench - Confidence Interval: leaderboard
Metric: Accuracy (%) on the 11 confidence interval 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
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3 | 63.6 |
| 2 | GPT-5.1 | 54.5 |
| 3 | Claude Sonnet 4.5 | 45.5 |
| 4 | Qwen 2.5 72B Instruct | 45.5 |
| 5 | Qwen 2.5 32B Instruct | 27.3 |
| 6 | Llama 3.1 8B Instruct | 18.2 |
| 7 | Qwen 2.5 7B Instruct | 18.2 |
| 8 | Qwen 3 8B (Non-reasoning) | 18.2 |
| 9 | GPT-4o Mini | 9.1 |
Interactive version: theaggregate.ai/benchmark?slug=statabench-confidence-interval · How It Works · Data refreshed daily, snapshot 2026-09-29.