Include

AI benchmark results and model performance

Type: percentageGeneral

Recorded Results

Average Score

70.49%

Score Range

40.60% - 85.60%

Leading Model (lowest score)

40.60% - Qwen 3.5 0.8B

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Qwen	Qwen 3.5 0.8B	02 Mar 2026	40.60%	-	Yes	Source
IBM	Granite 4.1 3B	29 Apr 2026	52.05%	5-shot	Yes	Source
Qwen	Qwen 3.5 2B	02 Mar 2026	55.40%	-	Yes	Source
IBM	Granite 4.1 8B	29 Apr 2026	58.89%	5-shot	Yes	Source
Qwen	Qwen 3 VL 4B Instruct	-	61.40%	-	Yes	-
Qwen	Qwen 3 4B Instruct 2507	-	64.60%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
Qwen	Qwen 3 4B SafeRL	-	64.60%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 4B Thinking 2507	-	64.60%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
Qwen	Qwen 3 Embedding 4B	-	64.60%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 Guard Gen 4B	-	64.60%	inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48)	Yes	-
Qwen	Qwen 3 Guard Stream 4B	-	64.60%	inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48)	Yes	-
Qwen	Qwen 3 Reranker 4B	-	64.60%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 VL 4B Thinking	-	64.60%	-	Yes	-
Qwen	Qwen 3 VL 8B Instruct	-	67%	-	Yes	-
IBM	Granite 4.1 30B	29 Apr 2026	67.26%	5-shot	Yes	Source
Qwen	Qwen 3 8B	-	69.50%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50)	Yes	-
Qwen	Qwen 3 Guard Stream 8B	-	69.50%	inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50)	Yes	-
Qwen	Qwen 3 VL 8B Thinking	-	69.50%	-	Yes	-
Qwen	Qwen 3 VL Embedding 8B	-	69.50%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50)	Yes	-
Qwen	Qwen 3 VL Reranker 8B	-	69.50%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50)	Yes	-
Qwen	Qwen 3.5 4B	02 Mar 2026	71%	-	Yes	Source
Qwen	Qwen 3 VL 30B A3B Instruct	-	71.60%	-	Yes	-
Qwen	Qwen 3 235B A22B	-	73.46%	-	Yes	Source
Qwen	Qwen 3 VL 32B Instruct	-	74%	-	Yes	-
Qwen	Qwen 3 VL 30B A3B Thinking	-	74.50%	-	Yes	-
Qwen	Qwen 3.5 9B	02 Mar 2026	75.60%	-	Yes	Source
Qwen	Qwen 3 VL 32B Thinking	-	76.30%	-	Yes	-
Qwen	Qwen 3 Next 80B A3B Instruct	-	78.90%	-	Yes	Source
Qwen	Qwen 3 Next 80B A3B Thinking	-	78.90%	-	Yes	Source
Qwen	Qwen 3.5 35B A3B	24 Feb 2026	79.70%	-	Yes	Source
Qwen	Qwen 3 VL 235B A22B Instruct	-	80%	-	Yes	-
Qwen	Qwen 3 VL 235B A22B Thinking	-	80%	-	Yes	-
Qwen	Qwen 3 235B A22B Thinking 2507	-	81%	-	Yes	Source
Qwen	Qwen 3.5 27B	24 Feb 2026	81.60%	-	Yes	Source
Qwen	Qwen 3.5 Flash	23 Feb 2026	81.60%	inferred family alias from qwen3.5-27b (score=0.4147; benches=81)	Yes	Source
Qwen	Qwen 3.5 122B A10B	24 Feb 2026	82.80%	-	Yes	Source
Qwen	Qwen 3.6 Plus	01 Apr 2026	85.10%	-	Yes	Source
Qwen	Qwen 3.5 397B A17B	16 Feb 2026	85.60%	-	Yes	Source