BFCL v2 Benchmark Leaderboard | Phaseo

BFCL v2

AI benchmark results and model performance

Type: percentageGeneral

Recorded Results

6

Average Score

71.00%

Score Range

63.60% - 77.30%

Leading Model (lowest score)

63.60% - Llama 3.1 Nemotron Nano 4B V1.1

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Nvidia	Llama 3.1 Nemotron Nano 4B V1.1	-	63.60%	inferred high-confidence family alias from llama-3.1-nemotron-nano-8b-v1 (score=0.5523; benches=7)	Yes	Source
Nvidia	Llama 3.1 Nemotron Nano 8B V1	18 Mar 2025	63.60%	-	Yes	Source
Nvidia	Llama 3.3 Nemotron Super 49B v1	18 Mar 2025	73.70%	-	Yes	Source
Nvidia	Llama 3.3 Nemotron Super 49B V1.5	-	73.70%	inferred version-family alias from llama-3.3-nemotron-super-49b-v1	Yes	Source
Nvidia	Llama 3.1 Nemotron Ultra 253B v1	07 Apr 2025	74.10%	-	Yes	Source
Meta	Llama 2 70B Chat	20 Jun 2023	77.30%	inferred family alias from llama-3.3-70b-instruct (score=0.3129; benches=9)	Yes	Source