Qwen 3.8 Max (0902) (Max): benchmark results

Provider: Alibaba. Released 2026-09-02. Access: API.

Aggregate Rating 1820 ± 25, rank #120 of 2245 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SuperCLUE General (July 2026) - Overall72.62Score100
SuperCLUE General (July 2026) - Math Reasoning78.95Score91.2
SuperCLUE General (July 2026) - Agentic Task Planning89.53Score88.2
SuperCLUE General (July 2026) - Hallucination Control86.19Score88.2
SuperCLUE General (July 2026) - Science Reasoning75.44Score85.3
SPU - Private - Raw0.39Mean Spearman correlation83.3
SPU Private Mean0.39Spearman correlation83.3
SuperCLUE General (July 2026) - Precise Instruction Following42.86Score82.4
ExplorationBench - AlienLogic76.2Held-out accuracy after exploration (%; Best@3: the highest 77.8
ExplorationBench - AlienCode64.3Held-out accuracy after exploration (%; Best@3: the highest 44.4
ExplorationBench - AlienCode (Open-Book)41Held-out accuracy with the complete rule set supplied before33.3
Terminal-Bench 4.0 (Claude Code)26.97Resolution Rate (%)19.2

Interactive version: theaggregate.ai/model?slug=qwen-3-8-max-0902-max · How It Works · Data refreshed daily, snapshot 2026-11-16.