AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    BFCL

    🏆 Leaderboard

    As of August 20, 2026, Llama 3.1 405B Instruct is #1 for BFCL at 88.5%. Ranked by the BFCL score 42 models in this index have a published BFCL score. BFCL leaderboard with live API prices. Berkeley Function Calling Leaderboard — tests accuracy and reliability of LLM function/tool calling.

    Updated August 20, 2026282 models33 providers
    Llama 3.1 405B InstructOSS
    Meta · Open Source
    		88.5%$1.78
    Llama 3.1 70B InstructOSS
    Meta · Open Source
    		84.8%$0.40
    Claude Opus 4.5
    Anthropic · Proprietary
    		77.5%$30.00
    Llama 3.1 8B InstructOSS
    Meta · Open Source
    		76.1%$0.06
    Nova 2 Sonic
    Amazon · Proprietary
    		74.5%$3.08
    Claude Sonnet 4.5
    Anthropic · Proprietary
    		73.2%$18.00
    Gemini 3 Pro
    Google · Proprietary
    		72.5%$14.00
    GLM-4.6OSS
    Z AI · Open Source
    		72.4%$2.80
    Qwen3 235B A22BOSS
    Qwen · Open Source
    		70.8%$0.20
    Qwen3 32BOSS
    Qwen · Open Source
    		70.3%$0.54
    Grok-4.1 Fast Reasoning
    xAI · Proprietary
    		69.6%$0.70
    Qwen3 30B A3BOSS
    Qwen · Open Source
    		69.1%$0.54
    Claude Haiku 4.5
    Anthropic · Proprietary
    		68.7%$6.00
    Nova Pro
    Amazon · Proprietary
    		68.4%$4.00
    Nova Lite
    Amazon · Proprietary
    		66.6%$0.30
    o3-mini
    OpenAI · Proprietary
    		65.1%$5.50
    o3
    OpenAI · Proprietary
    		63.0%$10.00
    Gemini 2.0 Flash
    Google · Proprietary
    		60.4%$0.50
    DeepSeek-V3OSS
    DeepSeek · Open Source
    		58.5%$1.37
    Grok-4.1 Fast Non-Reasoning
    xAI · Proprietary
    		58.3%$0.70
    DeepSeek-R1OSS
    DeepSeek · Open Source
    		57.5%$2.74
    DeepSeek-V3.2-ExpOSS
    DeepSeek · Open Source
    		56.7%$0.68
    Gemini 2.5 Flash
    Google · Proprietary
    		56.2%$2.80
    Nova Micro
    Amazon · Proprietary
    		56.2%$0.17
    GPT-5.2
    OpenAI · Proprietary
    		55.9%$15.75
    GPT-5 mini
    OpenAI · Proprietary
    		55.5%$2.25
    GPT-4.1
    OpenAI · Proprietary
    		54.0%$10.00
    o4-mini
    OpenAI · Proprietary
    		53.2%$5.50
    o1-mini
    OpenAI · Proprietary
    		52.2%$15.00
    Qwen3-235B-A22B-Instruct-2507OSS
    Qwen · Open Source
    		52.1%$0.95
    GPT-5 nano
    OpenAI · Proprietary
    		51.5%$0.45
    GPT-4.1 mini
    OpenAI · Proprietary
    		50.5%$2.00
    Command A+OSS
    Cohere · Open Source
    		46.5%$12.50
    Gemini 2.5 Flash-LiteOSS
    Google · Open Source
    		36.9%$0.50
    GPT-4.1 nano
    OpenAI · Proprietary
    		33.0%$0.50
    Llama 3.3 70B InstructOSS
    Meta · Open Source
    		31.9%$0.40
    Gemma 3 12BOSS
    Google · Open Source
    		30.4%$0.15
    Gemma 3 27BOSS
    Google · Open Source
    		29.5%$0.30
    Phi 4OSS
    Microsoft · Open Source
    		28.8%$0.21
    Llama 3.2 3B InstructOSS
    Meta · Open Source
    		21.9%$0.03lowest
    Gemma 3 4BOSS
    Google · Open Source
    		19.6%$0.06
    Ministral 8B InstructOSS
    Mistral · Open Source · via Mistral AI
    		11.1%$0.20
    ChatGPT-4o Latest
    OpenAI · Proprietary
    		—$12.50
    Claude 3 Haiku
    Anthropic · Proprietary
    		—$1.50
    Claude 3 Opus
    Anthropic · Proprietary
    		—$90.00
    Claude 3 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Claude 3.5 Haiku
    Anthropic · Proprietary
    		—$4.80
    Claude 3.5 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Claude 3.5 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Claude 3.7 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Showing 1–50 of 282 models

    Next step

    You found the model. Now ship the product.

    Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.

    Build with the APIsHave us build it with you

    The index

    All Large Language Models

    282 models across 33 providers. Search or jump to a lab — every model page stays linked here.

    OpenAI51Anthropic22Google25Cursor2xAI15DeepSeek16MiniMax6Qwen38AI21 Labs2Amazon5Baidu1ByteDance2Cohere3IBM1Inception1inclusionAI1LG AI Research1Meituan4Meta12Microsoft5Mistral23Moonshot AI9Nous Research1NVIDIA5Poolside2Sakana AI1StepFun1Tencent1Thinking Machines1Unisound1Upstage1Xiaomi3Z AI20

    Baidu

    1 models
    ERNIE 4.5

    Inception

    1 models
    Mercury 2

    inclusionAI

    1 models
    Ling-3.0-flash

    LG AI Research

    1 models
    K-EXAONE-236B-A23B

    Nous Research

    1 models
    Hermes 3 70B

    Sakana AI

    1 models
    Sakana Namazu

    StepFun

    1 models
    Step-3.5-Flash

    Tencent

    1 models
    Hy3

    Thinking Machines

    1 models
    Inkling-Small

    Unisound

    1 models
    U2

    Upstage

    1 models
    Solar Pro 4

    Which model leads BFCL right now?

    As of August 20, 2026, Llama 3.1 405B Instruct by Meta is #1 for BFCL at 88.5%. Ranked by the BFCL score This board also tracks BFCL. Next on the same board: Llama 3.1 70B Instruct and Claude Opus 4.5. This bfcl leaderboard ranks models by BFCL. Scores come from public evals. Prices are the live API rates in the table above.

    Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); Anthropic Claude API pricing (https://platform.claude.com/docs/en/about-claude/pricing); Gemini API pricing (https://ai.google.dev/gemini-api/docs/pricing)

    Top 8 for bfcl. Ranked by the BFCL score Input and output are dollars per million tokens.
    RankModelBFCLInput /MOutput /M
    1Llama 3.1 405B Instruct88.5%$0.89$0.89
    2Llama 3.1 70B Instruct84.8%$0.20$0.20
    3Claude Opus 4.577.5%$5.00$25.00
    4Llama 3.1 8B Instruct76.1%$0.03$0.03
    5Nova 2 Sonic74.5%$0.33$2.75
    6Claude Sonnet 4.573.2%$3.00$15.00
    7Gemini 3 Pro72.5%$2.00$12.00
    8GLM-4.672.4%$0.60$2.20

    Related LLM leaderboards

    LLM LeaderboardCodingMathAgenticReasoningWritingScienceFinanceLong ContextVisionOpen Source

    Individual benchmark pages

    Rank one eval at a time. All LLM benchmarks.

    HLESWE BenchHumanity's Last Exam (No Tools)Humanity's Last Exam (With Tools)Terminal-Bench 2.0Terminal-BenchTerminal-Bench 2.1Terminal-Bench 2Terminal-Bench 3.0ARC-AGI-1 Verified

    BFCL FAQ

    Who ranks #1 on the BFCL leaderboard?

    As of August 20, 2026, Llama 3.1 405B Instruct by Meta ranks #1 on BFCL at 88.5%. API pricing is $0.89/M input and $0.89/M output.

    What are the top models on BFCL?

    The current BFCL ranking as of August 20, 2026 is 1. Llama 3.1 405B Instruct at 88.5%; 2. Llama 3.1 70B Instruct at 84.8%; 3. Claude Opus 4.5 at 77.5%.

    Which bfcl model is the cheapest?

    Llama 3.2 3B Instruct is the cheapest scored model on this bfcl leaderboard at $0.01/M input and $0.02/M output ($0.03 blended). Llama 3.1 405B Instruct still leads BFCL at 88.5%.

    Should I always pick the #1 BFCL model?

    Not automatically. Llama 3.1 405B Instruct leads BFCL, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh BFCL against input/output price, context window, and related evals.

    How often is the BFCL leaderboard updated?

    Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 20, 2026. Treat it as a current index, not a one-off blog post.

    What is BFCL?

    Berkeley Function Calling Leaderboard — tests accuracy and reliability of LLM function/tool calling. This page ranks models that have published a BFCL score, with live API token prices on the same row.

    Where is the BFCL leaderboard?

    This page is the BFCL leaderboard. Models are sorted by BFCL, with input and output token prices on the same row so you can weigh score against cost. Official boards often omit price; that comparison is the point of this index.

    How is this BFCL ranking different from the official board?

    Official eval pages own the methodology. This page keeps the published BFCL score next to live API $/M so you can pick a production SKU, not only a trophy number.