Global PIQA
Global PIQA - physical reasoning benchmark across multiple languages and cultures.
Category
Multilingual
Max Score
—
Score Type
percent
Active
Yes
Model Scores
Scores for Global PIQA
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.5-4B |
78.90
|
01.02.2026 | Verified |
| Qwen3.5-122B-A10B |
98.96%
|
01.02.2026 | Verified |
| Qwen3.5-27B |
89.58%
|
01.02.2026 | Unverified |
| Qwen3.5-35B-A3B |
80.21%
|
01.02.2026 | Unverified |
| Qwen3-235B-A22B |
70.83%
|
01.02.2026 | Unverified |
| GPT-5-mini 2025-08-07 |
100.00%
|
01.02.2026 | Unverified |