PlanBench-XL - EGT Precision: leaderboard

Metric: Executed ground-truth datatype precision (%): share of the unique datatypes produced by the agent's executed tool calls that belong to the task's ground-truth datatype set, over the 327 PlanBench-XL retail tasks in the default block-free setting (1,665 tools, retrieval-limited tool visibility, temperature 0); higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)91.47
2Gemini 3.5 Flash85.29
3GPT-5.472.92
4GPT-5.4 Mini71.25
5DeepSeek V4 Flash65.57
6Qwen 3 32B62.36
7Llama 3.3 70B Instruct59.67
8Qwen 3 14B47.77
9Llama 3.1 8B Instruct41.33
10Qwen 3 8B35.31

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