physics benchmark
Global PIQA
Global PIQA is a multilingual commonsense reasoning benchmark that evaluates physical interaction knowledge across 100 languages and cultures. It tests AI systems' understanding of physical world knowledge in diverse cultural contexts through multiple choice questions about everyday situations requiring physical commonsense.
Updated Aug 7, 2026
Published models13
Registry coverage13
MetricScore
EvidenceB
Global PIQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | GO | 93.4% | 100.0% | 13 | C | |
| 2 | GO | 92.8% | 91.7% | 13 | C | |
| 3 | AC | 91.4% | 83.3% | 13 | C | |
| 4 | AC | 90.3% | 75.0% | 13 | C | |
| 5 | AC | 89.8% | 66.7% | 13 | C | |
| 6 | AC | 89.8% | 58.3% | 13 | C | |
| 7 | AC | 88.4% | 50.0% | 13 | C | |
| 8 | AC | 87.5% | 41.7% | 13 | C | |
| 9 | AC | 86.6% | 33.3% | 13 | C | |
| 10 | AC | 83.2% | 25.0% | 13 | C | |
| 11 | AC | 78.9% | 16.7% | 13 | C | |
| 12 | AC | 69.3% | 8.3% | 13 | C | |
| 13 | AC | 59.4% | 0.0% | 13 | C |
Score distribution
Top published rows on the benchmark's original scale.
Global PIQA highlights
The top published results on this benchmark's own scale.
What is Global PIQA?
Definition and scoring fields from the benchmark registry.
Global PIQA is a multilingual commonsense reasoning benchmark that evaluates physical interaction knowledge across 100 languages and cultures. It tests AI systems' understanding of physical world knowledge in diverse cultural contexts through multiple choice questions about everyday situations requiring physical commonsense.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Global PIQA
- Modality
- text
- Primary category
- physics
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- global-piqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Global PIQA.
Which model scores highest on Global PIQA?
Gemini 3 Pro is currently ranked first with 93.4%.
What does Global PIQA measure?
Global PIQA is a multilingual commonsense reasoning benchmark that evaluates physical interaction knowledge across 100 languages and cultures. It tests AI systems' understanding of physical world knowledge in diverse cultural contexts through multiple choice questions about everyday situations requiring physical commonsense.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
13 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.