INCLUDE

A multilingual benchmark used in provider tables to measure inclusive language coverage and cross-lingual understanding beyond common high-resource languages.

10 models

Higher is better.

1Claude Opus 5Anthropic89.8
2Claude Opus 4.8Anthropic87.6
3Qwen3.7 MaxAlibaba86.2
4Claude Opus 4.5Anthropic86.2
5Qwen3.5 397BAlibaba85.6
6Kimi K2.5Moonshot AI83.3
7Qwen3.7 PlusAlibaba83.0
8Qwen3 235B-A22BAlibaba75.6
9Qwen3 32BAlibaba70.9
10QwQ-32BAlibaba69.7

Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric: Multilingual benchmark
Tasks: Cross-lingual understanding
Authors: Qwen (2026)
Source: Qwen3.6 launch benchmarks ↗

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