Qwen3 235B A22B Instruct

Über dieses Modell

Qwen3 235B A22B Instruct is a Mixture-of-Experts model with 235B total parameters and 22B activated, featuring 128 experts with 8 activated per token. Native 262K context extended to 1M tokens via Dual Chunk Attention. Achieves SOTA: 83.0 MMLU-Pro, 70.3 AIME25, 41.8 ARC-AGI, 79.2 Arena-Hard v2, 51.8 LiveCodeBench, 70.9 BFCL-v3. Non-thinking mode focused on direct task execution with enhanced instruction following, logical reasoning, and long-tail knowledge across multiple languages. Dramatically more efficient than full 235B models.

Technische Daten

Fähigkeiten

Eingabe-Modalitäten

Ausgabe-Modalitäten

Reasoning

No

Knowledge horizon