Qwen 3: benchmark results

Provider: Alibaba.

Aggregate Rating 1630 ± 40, rank #751 of 10916 rated models, from 5 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Gapminder AI Worldview81.7Correct Rate (%)64.7
RubberDuckBench61.14Performance (%)47.4
TextQuests (No Clues)15.1Avg Game Progress (%)31.4
TextQuests (With Clues)29.8Avg Game Progress (%)28.6
FinChain45.99ChainEval (imported)20.8

Interactive version: theaggregate.ai/model?slug=qwen-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.