Global PIQA: leaderboard

Multilingual physical commonsense benchmark testing everyday interaction knowledge across many languages and cultural contexts.

Metric: Score (%). Source: qwen.ai. Status: saturated. 6 models tracked.

Top models

#ModelScore
1Qwen 3.7 Max91.4
2Claude Opus 4.6 (Thinking)91.2
3DeepSeek V4 Pro (Reasoning, Max Effort)90.5
4Qwen 3.6 Plus89.8
5GLM-5.1 (Thinking)89.5
6Kimi K2.6 (Thinking)89.2

Interactive version: theaggregate.ai/benchmark?slug=global-piqa · How It Works · Data refreshed daily, snapshot 2026-09-05.