BFCL-v3

AI benchmark results and model performance

Type: percentageAgents

Recorded Results

Average Score

67.95%

Score Range

60.80% - 77.80%

Leading Model (lowest score)

60.80% - Granite 4.1 3B

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
IBM	Granite 4.1 3B	29 Apr 2026	60.80%	-	Yes	Source
Qwen	Qwen 3 8B	-	63%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50)	Yes	-
Qwen	Qwen 3 Guard Stream 8B	-	63%	inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50)	Yes	-
Qwen	Qwen 3 VL 8B Thinking	-	63%	-	Yes	-
Qwen	Qwen 3 VL Embedding 8B	-	63%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50)	Yes	-
Qwen	Qwen 3 VL Reranker 8B	-	63%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50)	Yes	-
Qwen	Qwen 3 VL 4B Instruct	-	63.30%	-	Yes	-
Qwen	Qwen 3 VL 30B A3B Instruct	-	66.30%	-	Yes	-
Qwen	Qwen 3 VL 8B Instruct	-	66.30%	-	Yes	-
Qwen	Qwen 3 4B Instruct 2507	-	67.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
Qwen	Qwen 3 4B SafeRL	-	67.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 4B Thinking 2507	-	67.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
Qwen	Qwen 3 Embedding 4B	-	67.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 Guard Gen 4B	-	67.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48)	Yes	-
Qwen	Qwen 3 Guard Stream 4B	-	67.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48)	Yes	-
Qwen	Qwen 3 Reranker 4B	-	67.30%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 VL 4B Thinking	-	67.30%	-	Yes	-
Qwen	Qwen 3 VL 235B A22B Instruct	-	67.70%	-	Yes	-
IBM	Granite 4.1 8B	29 Apr 2026	68.27%	-	Yes	Source
Qwen	Qwen 3 VL 30B A3B Thinking	-	68.60%	-	Yes	-
Qwen	Qwen 3 VL 32B Instruct	-	70.20%	-	Yes	-
Qwen	Qwen 3 Next 80B A3B Instruct	-	70.30%	-	Yes	Source
Qwen	Qwen 3 VL 32B Thinking	-	71.70%	-	Yes	-
Qwen	Qwen 3 235B A22B Thinking 2507	-	71.90%	-	Yes	Source
Qwen	Qwen 3 VL 235B A22B Thinking	-	71.90%	-	Yes	-
Qwen	Qwen 3 Next 80B A3B Thinking	-	72%	-	Yes	Source
IBM	Granite 4.1 30B	29 Apr 2026	73.68%	-	Yes	Source
z.AI	GLM 4.5 Air	28 Jul 2025	76.40%	-	Yes	Source
z.AI	GLM 4.5	28 Jul 2025	77.80%	-	Yes	Source