StableToolBench - Win Rate — leaderboard

Metric: Average Win Rate (%). Source: huggingface.co. 10 models tracked.

Top models

#ModelScore
1Method Name 486.2
2GPT-4-Turbo-Preview (DFS)72.9
3GPT-4-Turbo-Preview (CoT)70
4Method Name 368.5
5GPT-4-0613 (DFS)64.2
6GPT-3.5-Turbo-0613 (DFS)63.3
7GPT-3.5-Turbo-1106 (DFS)58.5
8GPT-4-0613 (CoT)54.2
9GPT-3.5-Turbo-1106 (CoT)45.7
10ToolLLaMA v2 (CoT)32.4

Interactive version: theaggregate.ai/benchmark?slug=stabletoolbench-win-rate · How the rankings work · Data refreshed daily, snapshot 2026-07-22.