RealWorldQA leaderboard
RealWorldQA
1 models tested · Updated 2026-03-31 · Verified sources only
Qwen 3.6 Plus leads at 85.4%
1
Qwen 3.6 Plus
Alibaba · Blog/Alibaba · 2026-03-31
Leading on real-world image reasoning, ahead of Gemini 3 Pro (83.3).
85.4%
benchmark.space canonical public ledger of AI capability