llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

reasoning benchmark

BFCL v2 Leaderboard

Berkeley Function Calling Leaderboard (BFCL) v2 is a comprehensive benchmark for evaluating large language models' function calling capabilities. It features 2,251 question-function-answer pairs with enterprise and OSS-contributed functions, addressing data contamination and bias through live, user-contributed scenarios. The benchmark evaluates AST accuracy, executable accuracy, irrelevance detection, and relevance detection across multiple programming languages (Python, Java, JavaScript) and includes complex real-world function calling scenarios with multi-lingual prompts.

Updated Aug 17, 2026

Models5
Model coverage5
MetricScore
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

BFCL v2 Ranking

Higher score ranks better on this benchmark.

5 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelMELlama 3.3 70B InstructMetaScore77.3%Percentile100.0%Participants5EvidenceCEvaluatedAug 17, 2026
Rank02ModelNVLlama 3.1 Nemotron Ultra 253B v1NVIDIAScore74.1%Percentile75.0%Participants5EvidenceCEvaluatedAug 17, 2026
Rank03ModelNVLlama-3.3 Nemotron Super 49B v1NVIDIAScore73.7%Percentile50.0%Participants5EvidenceCEvaluatedAug 17, 2026
Rank04ModelMELlama 3.2 3B InstructMetaScore67.0%Percentile25.0%Participants5EvidenceCEvaluatedAug 17, 2026
Rank05ModelNVLlama 3.1 Nemotron Nano 8B V1NVIDIAScore63.6%Percentile0.0%Participants5EvidenceCEvaluatedAug 17, 2026

BFCL v2 Highlights

The leading models and scores on this benchmark.

Rank #1Llama 3.3 70B Instruct77.3%Rank #2Llama 3.1 Nemotron Ultra 253B v174.1%Rank #3Llama-3.3 Nemotron Super 49B v173.7%Rank #4Llama 3.2 3B Instruct67.0%

BFCL v2 Score Distribution

A closer view of the leading scores on this benchmark.

BFCL v2

The Top AI Models for BFCL v2

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

Ranking basisThis bfcl v2 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    ME
    Llama 3.3 70B InstructMeta
    Score
    77.3%
    Speed
    Up to 2,220 tok/s via Cerebras

    Strengths

    • Ranks #1 of 5 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BFCL v2, not total model capability
  2. 02
    NV
    Llama 3.1 Nemotron Ultra 253B v1NVIDIA
    Score
    74.1%

    Strengths

    • Ranks #2 of 5 compared models
    • 75th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BFCL v2, not total model capability
  3. 03
    NV
    Llama-3.3 Nemotron Super 49B v1NVIDIA
    Score
    73.7%

    Strengths

    • Ranks #3 of 5 compared models
    • 50th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BFCL v2, not total model capability
  4. 04
    ME
    Llama 3.2 3B InstructMeta
    Score
    67.0%
    Speed
    Up to 172 tok/s via DeepInfra

    Strengths

    • Ranks #4 of 5 compared models
    • 25th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BFCL v2, not total model capability
  5. 05
    NV
    Llama 3.1 Nemotron Nano 8B V1NVIDIA
    Score
    63.6%

    Strengths

    • Ranks #5 of 5 compared models
    • 0th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BFCL v2, not total model capability

Selection summary

Best AI Models for BFCL v2

Llama 3.3 70B Instruct currently leads BFCL v2 with 77.3%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Benchmark rank #1Llama 3.3 70B Instruct77.3% · Up to 2,220 tok/s via CerebrasBenchmark rank #2Llama 3.1 Nemotron Ultra 253B v174.1%Benchmark rank #3Llama-3.3 Nemotron Super 49B v173.7%

What is BFCL v2?

What BFCL v2 measures and how its scores work.

Berkeley Function Calling Leaderboard (BFCL) v2 is a comprehensive benchmark for evaluating large language models' function calling capabilities. It features 2,251 question-function-answer pairs with enterprise and OSS-contributed functions, addressing data contamination and bias through live, user-contributed scenarios. The benchmark evaluates AST accuracy, executable accuracy, irrelevance detection, and relevance detection across multiple programming languages (Python, Java, JavaScript) and includes complex real-world function calling scenarios with multi-lingual prompts.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
BFCL v2
Modality
text
Primary category
reasoning
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
bfcl-v2|llm-stats-current

Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about BFCL v2.

Which model scores highest on BFCL v2?

Llama 3.3 70B Instruct is currently ranked first with 77.3%.

What does BFCL v2 measure?

Berkeley Function Calling Leaderboard (BFCL) v2 is a comprehensive benchmark for evaluating large language models' function calling capabilities. It features 2,251 question-function-answer pairs with enterprise and OSS-contributed functions, addressing data contamination and bias through live, user-contributed scenarios. The benchmark evaluates AST accuracy, executable accuracy, irrelevance detection, and relevance detection across multiple programming languages (Python, Java, JavaScript) and includes complex real-world function calling scenarios with multi-lingual prompts.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

5 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.