physics benchmark
Global PIQA Leaderboard
Global PIQA is a multilingual commonsense reasoning benchmark covering physical interaction knowledge across 100 languages and cultures.
Updated Sep 5, 2026
Models13
Model coverage13
MetricScore
EvidenceB
Global PIQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score93.40% | Percentile100.00% | Participants13 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score92.80% | Percentile91.67% | Participants13 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score91.40% | Percentile83.33% | Participants13 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score90.30% | Percentile75.00% | Participants13 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score89.80% | Percentile66.67% | Participants13 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score89.80% | Percentile58.33% | Participants13 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score88.40% | Percentile50.00% | Participants13 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score87.50% | Percentile41.67% | Participants13 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score86.60% | Percentile33.33% | Participants13 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score83.20% | Percentile25.00% | Participants13 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score78.90% | Percentile16.67% | Participants13 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score69.30% | Percentile8.33% | Participants13 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score59.40% | Percentile0.00% | Participants13 | EvidenceC | Evaluated |
Global PIQA Highlights
The leading models and scores on this benchmark.
Global PIQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Global PIQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Global PIQA?
What Global PIQA measures and how its scores work.
Global PIQA is a benchmark that uses multiple-choice questions about everyday situations requiring physical commonsense.
It measures AI systems' understanding of physical world knowledge in diverse cultural contexts.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Global PIQA
- Modality
- text
- Primary category
- physics
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Global PIQA.
Which model scores highest on Global PIQA?
Gemini 3 Pro is currently ranked first with 93.40%.
What are the top three models on Global PIQA?
The current leaders are Gemini 3 Pro (93.40%), Gemini 3 Flash (92.80%), and Qwen3.7 Max (91.40%).
Which Global PIQA model has the lowest official input price?
Qwen3.5-35B-A3B has the lowest matched official input price at $0.25 input / $2.0 output per 1M tokens.
Which models are fastest among Global PIQA results?
The fastest matched records are Gemini 3 Flash (124.32 tok/s via Google) and Gemini 3 Pro (90.00 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.