Qwen 3.8 Max (Max): benchmark results

Provider: Alibaba. Released 2026-08-03. Access: API.

Unified ELO 1752 ± 1, rank #33 of 3078 rated models, from 14 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SuperCLUE General (July 2026) - Agentic Task Planning90.94Score94.1
SuperCLUE General (July 2026) - Precise Instruction Following43.81Score94.1
SuperCLUE General (July 2026) - Overall71.48Score88.2
SuperCLUE General (July 2026) - Hallucination Control86.08Score79.4
SuperCLUE General (July 2026) - Math Reasoning77.19Score76.5
ASI-Bench (Claude Code)38.87Scientific Score (0-100)75
ASI-Bench (Claude Code) - B1 Full Guidance59.14Scientific Score (0-100)75
ASI-Bench (Claude Code) - B4 Goal + Distractors34.46Scientific Score (0-100)75
Bug Hunt Bench - VS Code Extension12.3Planted Bugs Fixed (out of 45)70.1
Bug Hunt Bench25.7Planted Bugs Fixed (out of 105)67.2
Bug Hunt Bench - LMS13.3Planted Bugs Fixed (out of 60)67.2
SuperCLUE General (July 2026) - Science Reasoning71.93Score64.7

Interactive version: theaggregate.ai/model?slug=qwen-3-8-max-max · How It Works · Data refreshed daily, snapshot 2026-09-19.