Wikibench

Global PIQA

reasoning

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.

Leaderboard

Showing 12 of 12 results

  1. Gemini 3 Pro
    93.4%
    i
  2. Gemini 3 Flash
    92.8%
    i
  3. Qwen3.7 Max
    91.4%
    i
  4. Qwen3.5-397B-A17B
    89.8%
    i
  5. Qwen3.6 Plus
    89.8%
    i
  6. Qwen3.5-122B-A10B
    88.4%
    i
  7. Qwen3.5-27B
    87.5%
    i
  8. Qwen3.5-35B-A3B
    86.6%
    i
  9. Qwen3.5-9B
    83.2%
    i
  10. Qwen3.5-4B
    78.9%
    i
  11. Qwen3.5-2B
    69.3%
    i
  12. Qwen3.5-0.8B
    59.4%
    i