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
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Max | 91.4 |
| 2 | Claude Opus 4.6 (Thinking) | 91.2 |
| 3 | DeepSeek V4 Pro (Reasoning, Max Effort) | 90.5 |
| 4 | Qwen 3.6 Plus | 89.8 |
| 5 | GLM-5.1 (Thinking) | 89.5 |
| 6 | Kimi K2.6 (Thinking) | 89.2 |
Interactive version: theaggregate.ai/benchmark?slug=global-piqa · How It Works · Data refreshed daily, snapshot 2026-09-05.