Skip to content

NOVA-63

A broad multilingual benchmark row from Qwen's launch comparisons intended to measure cross-lingual capability beyond a single language family.

7 models

Higher is better.

  1. 1Qwen3.5 397BAlibaba59.1
  2. 2Qwen3.7 MaxAlibaba59.0
  3. 3Qwen3.7 PlusAlibaba58.8
  4. 4Qwen3.6 PlusAlibaba57.9
  5. 5Claude Opus 4.5Anthropic56.7
  6. 6Kimi K2.5Moonshot AI56.0
  7. 7GLM-5Z.AI55.1
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Cross-lingual benchmark
Tasks
Broad multilingual evaluation
Authors
Qwen (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.