{
  "data": {
    "area": "agent-tasks",
    "attribution": "Berkeley Function Calling Leaderboard, UC Berkeley (Gorilla), Apache 2.0",
    "cadence": "irregular",
    "categories": [
      "inference",
      "open-weights"
    ],
    "ceiling": 100,
    "competitor": "",
    "data": "https://github.com/HuanzhiMao/BFCL-Result",
    "direction": "higher",
    "floor": 0,
    "json": "https://www.anchorterminal.com/benchmarks/bfcl/index.json",
    "licence": "Apache-2.0",
    "licenceUrl": "https://github.com/HuanzhiMao/BFCL-Result/blob/main/LICENSE",
    "measures": "Whether a model calls functions correctly: simple, parallel and multi-turn calls, knowing when no function fits, web search and memory tasks, run by the Berkeley team on every model, with native function calling and with prompting as separate rows.",
    "method": "https://gorilla.cs.berkeley.edu/leaderboard.html",
    "models": 5,
    "name": "Berkeley Function Calling Leaderboard (BFCL)",
    "newest": "2025-12-16",
    "page": "https://www.anchorterminal.com/benchmarks/bfcl/",
    "read": "2026-11-20",
    "results": 7,
    "runBy": "UC Berkeley (Gorilla)",
    "saturated": false,
    "slug": "bfcl",
    "status": "stale",
    "unit": "% overall accuracy",
    "versions": [
      {
        "rows": [
          {
            "as": "Qwen3-30B-A3B-Instruct-2507",
            "date": "2025-12-16",
            "listing": "qwen3-30b-a3b-instruct-2507",
            "model": "qwen3-30b-a3b-instruct-2507",
            "name": "Qwen3-30B-A3B-Instruct-2507",
            "of": 5,
            "rank": 1,
            "runBy": "UC Berkeley (Gorilla)",
            "score": 41.39,
            "setting": {
              "mode": "FC"
            },
            "tier": "independent",
            "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
            "version": "v4"
          },
          {
            "as": "Qwen3-30B-A3B-Instruct-2507",
            "date": "2025-12-16",
            "listing": "qwen3-30b-a3b-instruct-2507",
            "model": "qwen3-30b-a3b-instruct-2507",
            "name": "Qwen3-30B-A3B-Instruct-2507",
            "runBy": "UC Berkeley (Gorilla)",
            "score": 36.7,
            "setting": {
              "mode": "Prompt"
            },
            "tier": "independent",
            "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
            "version": "v4"
          },
          {
            "as": "Qwen3-4B-Instruct-2507",
            "date": "2025-12-16",
            "listing": "qwen3-4b-instruct-2507",
            "model": "qwen3-4b-instruct-2507",
            "name": "Qwen3-4B-Instruct-2507",
            "of": 5,
            "rank": 2,
            "runBy": "UC Berkeley (Gorilla)",
            "score": 35.68,
            "setting": {
              "mode": "FC"
            },
            "tier": "independent",
            "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
            "version": "v4"
          },
          {
            "as": "Qwen3-4B-Instruct-2507",
            "date": "2025-12-16",
            "listing": "qwen3-4b-instruct-2507",
            "model": "qwen3-4b-instruct-2507",
            "name": "Qwen3-4B-Instruct-2507",
            "runBy": "UC Berkeley (Gorilla)",
            "score": 35.52,
            "setting": {
              "mode": "Prompt"
            },
            "tier": "independent",
            "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
            "version": "v4"
          },
          {
            "as": "Command R7B",
            "date": "2025-12-16",
            "listing": "cohere-chat",
            "model": "command-r7b",
            "name": "Command R7B",
            "of": 5,
            "rank": 3,
            "runBy": "UC Berkeley (Gorilla)",
            "score": 32.07,
            "setting": {
              "mode": "FC"
            },
            "tier": "independent",
            "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
            "version": "v4"
          },
          {
            "as": "Llama-3.3-70B-Instruct",
            "date": "2025-12-16",
            "listing": "sambanova",
            "model": "llama-3-3-70b",
            "name": "Llama 3.3 70B",
            "of": 5,
            "rank": 4,
            "runBy": "UC Berkeley (Gorilla)",
            "score": 31.9,
            "setting": {
              "mode": "FC"
            },
            "tier": "independent",
            "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
            "version": "v4"
          },
          {
            "as": "Amazon-Nova-2-Lite-v1:0",
            "date": "2025-12-16",
            "listing": "amazon-bedrock",
            "model": "amazon-nova-2-lite",
            "name": "Amazon Nova 2 Lite",
            "of": 5,
            "rank": 5,
            "runBy": "UC Berkeley (Gorilla)",
            "score": 27.1,
            "setting": {
              "mode": "FC"
            },
            "tier": "independent",
            "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
            "version": "v4"
          }
        ],
        "version": "v4"
      }
    ]
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/benchmarks/bfcl/",
    "json": "https://www.anchorterminal.com/benchmarks/bfcl/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/benchmarks/bfcl/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/benchmarks/bfcl/index.min.md"
  },
  "markdown": "Whether a model calls functions correctly: simple, parallel and multi-turn calls, knowing when no function fits, web search and memory tasks, run by the Berkeley team on every model, with native function calling and with prompting as separate rows.\n\n- Score: % overall accuracy, higher is better\n- Run by: UC Berkeley (Gorilla)\n- Status: Stale, newest result 16 December 2025, nothing new in six months\n- Updated: irregular\n- Data: https://github.com/HuanzhiMao/BFCL-Result (Apache-2.0, https://github.com/HuanzhiMao/BFCL-Result/blob/main/LICENSE), read 2026-11-20\n- Method: https://gorilla.cs.berkeley.edu/leaderboard.html\n\n## Results\n\n5 models we list, each at its best setting, best first.\n\n| # | Model | Score | Range | Who ran it | Setting | Date | Source |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | [Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507.md) | 41.4% |  | Independent | mode FC | 2025-12-16 | https://gorilla.cs.berkeley.edu/leaderboard.html |\n| 2 | [Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/tools/qwen3-4b-instruct-2507.md) | 35.7% |  | Independent | mode FC | 2025-12-16 | https://gorilla.cs.berkeley.edu/leaderboard.html |\n| 3 | [Command R7B](https://www.anchorterminal.com/tools/cohere-chat.md) | 32.1% |  | Independent | mode FC | 2025-12-16 | https://gorilla.cs.berkeley.edu/leaderboard.html |\n| 4 | [Llama 3.3 70B](https://www.anchorterminal.com/tools/sambanova.md) | 31.9% |  | Independent | mode FC | 2025-12-16 | https://gorilla.cs.berkeley.edu/leaderboard.html |\n| 5 | [Amazon Nova 2 Lite](https://www.anchorterminal.com/tools/amazon-bedrock.md) | 27.1% |  | Independent | mode FC | 2025-12-16 | https://gorilla.cs.berkeley.edu/leaderboard.html |\n\nEvery setting, 7 rows:\n\n| Model | As named | Score | Who ran it | Setting | Date |\n| --- | --- | --- | --- | --- | --- |\n| Qwen3-30B-A3B-Instruct-2507 | Qwen3-30B-A3B-Instruct-2507 | 41.4% | Independent | mode FC | 2025-12-16 |\n| Qwen3-30B-A3B-Instruct-2507 | Qwen3-30B-A3B-Instruct-2507 | 36.7% | Independent | mode Prompt | 2025-12-16 |\n| Qwen3-4B-Instruct-2507 | Qwen3-4B-Instruct-2507 | 35.7% | Independent | mode FC | 2025-12-16 |\n| Qwen3-4B-Instruct-2507 | Qwen3-4B-Instruct-2507 | 35.5% | Independent | mode Prompt | 2025-12-16 |\n| Command R7B | Command R7B | 32.1% | Independent | mode FC | 2025-12-16 |\n| Llama 3.3 70B | Llama-3.3-70B-Instruct | 31.9% | Independent | mode FC | 2025-12-16 |\n| Amazon Nova 2 Lite | Amazon-Nova-2-Lite-v1:0 | 27.1% | Independent | mode FC | 2025-12-16 |\n\nA rank is among the models we list with a result, not a place on the whole leaderboard, and a model offered by several hosts is shown once, on its own listing. These results don't move our grades.\n\nData: Berkeley Function Calling Leaderboard, UC Berkeley (Gorilla), Apache 2.0, Apache-2.0. All benchmarks: https://www.anchorterminal.com/benchmarks/index.md\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-22",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Benchmarks",
        "url": "https://www.anchorterminal.com/benchmarks/"
      },
      {
        "name": "Berkeley Function Calling Leaderboard (BFCL)",
        "url": ""
      }
    ],
    "description": "Berkeley Function Calling Leaderboard (BFCL) results for 5 AI models we list, run by UC Berkeley (Gorilla), with each result's setting, date and source.",
    "facts": [
      "5 models",
      "UC Berkeley (Gorilla)",
      "Stale"
    ],
    "h1": "Berkeley Function Calling Leaderboard (BFCL)",
    "image": "https://www.anchorterminal.com/assets/og/benchmarks-bfcl.png",
    "path": "/benchmarks/bfcl/",
    "published": "",
    "section": "benchmarks",
    "title": "Berkeley Function Calling Leaderboard (BFCL) results | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-21",
    "url": "https://www.anchorterminal.com/benchmarks/bfcl/"
  },
  "tokens": {
    "markdown": 900,
    "slim": 830
  },
  "version": 1
}
