ZEROBench

AI benchmark results and model performance

Type: numericalMultimodal

4.79

0.04 - 33

0.04 - Qwen 3 VL 235B A22B Thinking

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Qwen	Qwen 3 VL 235B A22B Thinking	-	0.04	-	Yes	-
Qwen	Qwen 3.5 35B A3B	24 Feb 2026	0.08	Raw score: 8	Yes	Source
Qwen	Qwen 3.5 122B A10B	24 Feb 2026	0.09	Raw score: 9	Yes	Source
Qwen	Qwen 3.5 27B	24 Feb 2026	0.10	Raw score: 10	Yes	Source
Qwen	Qwen 3.5 Flash	23 Feb 2026	0.10	inferred family alias from qwen3.5-27b (score=0.4147; benches=81)	Yes	Source
Moonshot	Kimi K2.5	27 Jan 2026	0.11	w/ tools (11.0)	Yes	Source
Meta	Muse Spark	08 Apr 2026	33	Multi-step	Yes	Source