{
  "version": "https://jsonfeed.org/version/1.1",
  "title": "Model Follower: Call tools and APIs",
  "home_page_url": "https://openmodeldrops.com/for/tool-use/",
  "feed_url": "https://openmodeldrops.com/feeds/for/tool-use.json",
  "description": "Models with measured (third-party leaderboard) or author-reported evidence for \"Call tools and APIs\", dated by when the evidence was observed.",
  "language": "en",
  "items": [
    {
      "id": "d5d585b066c7eccc2e3e",
      "url": "https://openmodeldrops.com/models/google/gemma-3-1b-it/",
      "title": "gemma-3-1b-it: BFCL 7.17",
      "content_text": "google/gemma-3-1b-it has measured evidence for \"Call tools and APIs\": BFCL 7.17 (Prompt). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241862+00:00.",
      "date_published": "2026-10-25T06:54:09.241862+00:00",
      "_diff": {
        "model_id": "google/gemma-3-1b-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 7.17",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241862+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "f8e7b038db980076ab10",
      "url": "https://openmodeldrops.com/models/google/gemma-3-4b-it/",
      "title": "gemma-3-4b-it: BFCL 19.62",
      "content_text": "google/gemma-3-4b-it has measured evidence for \"Call tools and APIs\": BFCL 19.62 (Prompt). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241809+00:00.",
      "date_published": "2026-10-25T06:54:09.241809+00:00",
      "_diff": {
        "model_id": "google/gemma-3-4b-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 19.62",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241809+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "8c6655f3c0f0ff3c8698",
      "url": "https://openmodeldrops.com/models/meta-llama/Llama-3.2-3B-Instruct/",
      "title": "Llama-3.2-3B-Instruct: BFCL 21.95",
      "content_text": "meta-llama/Llama-3.2-3B-Instruct has measured evidence for \"Call tools and APIs\": BFCL 21.95 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241784+00:00.",
      "date_published": "2026-10-25T06:54:09.241784+00:00",
      "_diff": {
        "model_id": "meta-llama/Llama-3.2-3B-Instruct",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 21.95",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241784+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "5b53ca3df96ce1f68c08",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-0.6B/",
      "title": "Qwen3-0.6B: BFCL 23.93",
      "content_text": "Qwen/Qwen3-0.6B has measured evidence for \"Call tools and APIs\": BFCL 23.93 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241738+00:00.",
      "date_published": "2026-10-25T06:54:09.241738+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-0.6B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 23.93",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241738+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "4cee21b8cea6bcb102e8",
      "url": "https://openmodeldrops.com/models/meta-llama/Llama-3.1-8B-Instruct/",
      "title": "Llama-3.1-8B-Instruct: BFCL 25.83",
      "content_text": "meta-llama/Llama-3.1-8B-Instruct has measured evidence for \"Call tools and APIs\": BFCL 25.83 (Prompt). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241697+00:00.",
      "date_published": "2026-10-25T06:54:09.241697+00:00",
      "_diff": {
        "model_id": "meta-llama/Llama-3.1-8B-Instruct",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 25.83",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241697+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "c4bc385ca218a973edbf",
      "url": "https://openmodeldrops.com/models/meta-llama/Llama-4-Scout-17B-16E-Instruct/",
      "title": "Llama-4-Scout-17B-16E-Instruct: BFCL 28.13",
      "content_text": "meta-llama/Llama-4-Scout-17B-16E-Instruct has measured evidence for \"Call tools and APIs\": BFCL 28.13 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241621+00:00.",
      "date_published": "2026-10-25T06:54:09.241621+00:00",
      "_diff": {
        "model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 28.13",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241621+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "06a9f0d049ec7f36fcee",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-1.7B/",
      "title": "Qwen3-1.7B: BFCL 28.41",
      "content_text": "Qwen/Qwen3-1.7B has measured evidence for \"Call tools and APIs\": BFCL 28.41 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241610+00:00.",
      "date_published": "2026-10-25T06:54:09.241610+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-1.7B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 28.41",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241610+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "1ded5b78615803118ea3",
      "url": "https://openmodeldrops.com/models/microsoft/phi-4/",
      "title": "phi-4: BFCL 28.79",
      "content_text": "microsoft/phi-4 has measured evidence for \"Call tools and APIs\": BFCL 28.79 (Prompt). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241599+00:00.",
      "date_published": "2026-10-25T06:54:09.241599+00:00",
      "_diff": {
        "model_id": "microsoft/phi-4",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 28.79",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241599+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "10bd29eb7d2475138a03",
      "url": "https://openmodeldrops.com/models/google/gemma-3-27b-it/",
      "title": "gemma-3-27b-it: BFCL 29.47",
      "content_text": "google/gemma-3-27b-it has measured evidence for \"Call tools and APIs\": BFCL 29.47 (Prompt). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241583+00:00.",
      "date_published": "2026-10-25T06:54:09.241583+00:00",
      "_diff": {
        "model_id": "google/gemma-3-27b-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 29.47",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241583+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "4d42b4fe0e7818c924a9",
      "url": "https://openmodeldrops.com/models/google/gemma-3-12b-it/",
      "title": "gemma-3-12b-it: BFCL 30.43",
      "content_text": "google/gemma-3-12b-it has measured evidence for \"Call tools and APIs\": BFCL 30.43 (Prompt). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241521+00:00.",
      "date_published": "2026-10-25T06:54:09.241521+00:00",
      "_diff": {
        "model_id": "google/gemma-3-12b-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 30.43",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241521+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "f3be4e9a34ed699a8919",
      "url": "https://openmodeldrops.com/models/meta-llama/Llama-3.3-70B-Instruct/",
      "title": "Llama-3.3-70B-Instruct: BFCL 31.9",
      "content_text": "meta-llama/Llama-3.3-70B-Instruct has measured evidence for \"Call tools and APIs\": BFCL 31.9 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241493+00:00.",
      "date_published": "2026-10-25T06:54:09.241493+00:00",
      "_diff": {
        "model_id": "meta-llama/Llama-3.3-70B-Instruct",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 31.9",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241493+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "1d408f575afccb83c823",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-4B-Instruct-2507/",
      "title": "Qwen3-4B-Instruct-2507: BFCL 35.68",
      "content_text": "Qwen/Qwen3-4B-Instruct-2507 has measured evidence for \"Call tools and APIs\": BFCL 35.68 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241443+00:00.",
      "date_published": "2026-10-25T06:54:09.241443+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-4B-Instruct-2507",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 35.68",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241443+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "d56ac873df5fd435faad",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-14B/",
      "title": "Qwen3-14B: BFCL 41.03",
      "content_text": "Qwen/Qwen3-14B has measured evidence for \"Call tools and APIs\": BFCL 41.03 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241371+00:00.",
      "date_published": "2026-10-25T06:54:09.241371+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-14B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 41.03",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241371+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "4e0ca19102634bece17d",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-30B-A3B-Instruct-2507/",
      "title": "Qwen3-30B-A3B-Instruct-2507: BFCL 41.39",
      "content_text": "Qwen/Qwen3-30B-A3B-Instruct-2507 has measured evidence for \"Call tools and APIs\": BFCL 41.39 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241354+00:00.",
      "date_published": "2026-10-25T06:54:09.241354+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 41.39",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241354+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "c729139a9bc2695de0d3",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-8B/",
      "title": "Qwen3-8B: BFCL 42.57",
      "content_text": "Qwen/Qwen3-8B has measured evidence for \"Call tools and APIs\": BFCL 42.57 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241337+00:00.",
      "date_published": "2026-10-25T06:54:09.241337+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-8B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 42.57",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241337+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "6423492a6024b466ea38",
      "url": "https://openmodeldrops.com/models/Salesforce/Llama-xLAM-2-8b-fc-r/",
      "title": "Llama-xLAM-2-8b-fc-r: BFCL 46.68",
      "content_text": "Salesforce/Llama-xLAM-2-8b-fc-r has measured evidence for \"Call tools and APIs\": BFCL 46.68 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241306+00:00.",
      "date_published": "2026-10-25T06:54:09.241306+00:00",
      "_diff": {
        "model_id": "Salesforce/Llama-xLAM-2-8b-fc-r",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 46.68",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241306+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "9e3545ea6904c7ce9419",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-32B/",
      "title": "Qwen3-32B: BFCL 48.71",
      "content_text": "Qwen/Qwen3-32B has measured evidence for \"Call tools and APIs\": BFCL 48.71 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241262+00:00.",
      "date_published": "2026-10-25T06:54:09.241262+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-32B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 48.71",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241262+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "5a9cdd9af9c85f6d855d",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-235B-A22B-Instruct-2507/",
      "title": "Qwen3-235B-A22B-Instruct-2507: BFCL 52.15",
      "content_text": "Qwen/Qwen3-235B-A22B-Instruct-2507 has measured evidence for \"Call tools and APIs\": BFCL 52.15 (Prompt). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241228+00:00.",
      "date_published": "2026-10-25T06:54:09.241228+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 52.15",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241228+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "f8c9cf0efa8f7a67bf24",
      "url": "https://openmodeldrops.com/models/deepseek-ai/DeepSeek-V3.2-Exp/",
      "title": "DeepSeek-V3.2-Exp: BFCL 54.12",
      "content_text": "deepseek-ai/DeepSeek-V3.2-Exp has measured evidence for \"Call tools and APIs\": BFCL 54.12 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241198+00:00.",
      "date_published": "2026-10-25T06:54:09.241198+00:00",
      "_diff": {
        "model_id": "deepseek-ai/DeepSeek-V3.2-Exp",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 54.12",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241198+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "cbf3736db337f7c2fcb8",
      "url": "https://openmodeldrops.com/models/moonshotai/Kimi-K2-Instruct/",
      "title": "Kimi-K2-Instruct: BFCL 59.06",
      "content_text": "moonshotai/Kimi-K2-Instruct has measured evidence for \"Call tools and APIs\": BFCL 59.06 (FC). Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241146+00:00.",
      "date_published": "2026-10-25T06:54:09.241146+00:00",
      "_diff": {
        "model_id": "moonshotai/Kimi-K2-Instruct",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 59.06",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241146+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "b1f7bfbf7300d5a78cc3",
      "url": "https://openmodeldrops.com/models/zai-org/GLM-4.6/",
      "title": "GLM-4.6: BFCL 72.38",
      "content_text": "zai-org/GLM-4.6 has measured evidence for \"Call tools and APIs\": BFCL 72.38. Source: https://gorilla.cs.berkeley.edu/leaderboard.html. Observed at 2026-10-25T06:54:09.241091+00:00.",
      "date_published": "2026-10-25T06:54:09.241091+00:00",
      "_diff": {
        "model_id": "zai-org/GLM-4.6",
        "field": "use_case:tool-use",
        "old": null,
        "new": "BFCL 72.38",
        "source_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "observed_at": "2026-10-25T06:54:09.241091+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "71e8c6a081e8b31fb21a",
      "url": "https://openmodeldrops.com/models/moonshotai/Kimi-K3/",
      "title": "Kimi-K3: Author reports toolathlon_verified 76.5",
      "content_text": "moonshotai/Kimi-K3 has author-reported evidence for \"Call tools and APIs\": Author reports toolathlon_verified 76.5. Source: https://huggingface.co/moonshotai/Kimi-K3/raw/main/.eval_results/moonshotai__Kimi-K3.yaml. Observed at 2026-10-24T21:31:33Z.",
      "date_published": "2026-10-24T21:31:33Z",
      "_diff": {
        "model_id": "moonshotai/Kimi-K3",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports toolathlon_verified 76.5",
        "source_url": "https://huggingface.co/moonshotai/Kimi-K3/raw/main/.eval_results/moonshotai__Kimi-K3.yaml",
        "observed_at": "2026-10-24T21:31:33Z",
        "kind": "usecase"
      }
    },
    {
      "id": "ea9f66c16d023e034688",
      "url": "https://openmodeldrops.com/models/Nanbeige/Nanbeige4.1-3B/",
      "title": "Nanbeige4.1-3B: Author reports BFCL-V4 56.50",
      "content_text": "Nanbeige/Nanbeige4.1-3B has author-reported evidence for \"Call tools and APIs\": Author reports BFCL-V4 56.50. Source: https://huggingface.co/Nanbeige/Nanbeige4.1-3B/raw/main/README.md. Observed at 2026-10-07T20:24:14.555408+00:00.",
      "date_published": "2026-10-07T20:24:14.555408+00:00",
      "_diff": {
        "model_id": "Nanbeige/Nanbeige4.1-3B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL-V4 56.50",
        "source_url": "https://huggingface.co/Nanbeige/Nanbeige4.1-3B/raw/main/README.md",
        "observed_at": "2026-10-07T20:24:14.555408+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "915c7f6eed57ae832b5d",
      "url": "https://openmodeldrops.com/models/nvidia/Llama-3.1-Nemotron-Nano-8B-v1/",
      "title": "Llama-3.1-Nemotron-Nano-8B-v1: Author reports BFCL v2 Live 63.9%",
      "content_text": "nvidia/Llama-3.1-Nemotron-Nano-8B-v1 has author-reported evidence for \"Call tools and APIs\": Author reports BFCL v2 Live 63.9% (Reasoning Off). Source: https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1/raw/main/README.md. Observed at 2026-10-07T20:23:23.648226+00:00.",
      "date_published": "2026-10-07T20:23:23.648226+00:00",
      "_diff": {
        "model_id": "nvidia/Llama-3.1-Nemotron-Nano-8B-v1",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL v2 Live 63.9%",
        "source_url": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1/raw/main/README.md",
        "observed_at": "2026-10-07T20:23:23.648226+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "ede5a96e00b9615c2848",
      "url": "https://openmodeldrops.com/models/ornith-ai/Ornith-1.5-9B/",
      "title": "Ornith-1.5-9B: Author reports Toolathlon-Verified 41.2",
      "content_text": "ornith-ai/Ornith-1.5-9B has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon-Verified 41.2. Source: https://huggingface.co/ornith-ai/Ornith-1.5-9B/raw/main/README.md. Observed at 2026-10-07T20:23:11.012299+00:00.",
      "date_published": "2026-10-07T20:23:11.012299+00:00",
      "_diff": {
        "model_id": "ornith-ai/Ornith-1.5-9B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon-Verified 41.2",
        "source_url": "https://huggingface.co/ornith-ai/Ornith-1.5-9B/raw/main/README.md",
        "observed_at": "2026-10-07T20:23:11.012299+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "ebb0d34562c9217c3e2b",
      "url": "https://openmodeldrops.com/models/google/gemma-4-26B-A4B-it-assistant/",
      "title": "gemma-4-26B-A4B-it-assistant: Author reports Tau2 (average over 3) 68.2%",
      "content_text": "google/gemma-4-26B-A4B-it-assistant has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 68.2% (Gemma 4 26B A4B). Source: https://huggingface.co/google/gemma-4-26B-A4B-it-assistant/raw/main/README.md. Observed at 2026-10-07T20:22:38.751487+00:00.",
      "date_published": "2026-10-07T20:22:38.751487+00:00",
      "_diff": {
        "model_id": "google/gemma-4-26B-A4B-it-assistant",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 68.2%",
        "source_url": "https://huggingface.co/google/gemma-4-26B-A4B-it-assistant/raw/main/README.md",
        "observed_at": "2026-10-07T20:22:38.751487+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "ddb55674657989aba46b",
      "url": "https://openmodeldrops.com/models/google/functiongemma-270m-it/",
      "title": "functiongemma-270m-it: Author reports BFCL Irrelevance 73.7",
      "content_text": "google/functiongemma-270m-it has author-reported evidence for \"Call tools and APIs\": Author reports BFCL Irrelevance 73.7 (0-shot). Source: https://huggingface.co/google/functiongemma-270m-it/raw/main/README.md. Observed at 2026-10-07T20:22:05.191400+00:00.",
      "date_published": "2026-10-07T20:22:05.191400+00:00",
      "_diff": {
        "model_id": "google/functiongemma-270m-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL Irrelevance 73.7",
        "source_url": "https://huggingface.co/google/functiongemma-270m-it/raw/main/README.md",
        "observed_at": "2026-10-07T20:22:05.191400+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "cec558c0d2bc95dee011",
      "url": "https://openmodeldrops.com/models/poolside/Laguna-S-2.1/",
      "title": "Laguna-S-2.1: Author reports Toolathlon Verified 49.7%",
      "content_text": "poolside/Laguna-S-2.1 has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon Verified 49.7% (118B-A8B). Source: https://huggingface.co/poolside/Laguna-S-2.1/raw/main/README.md. Observed at 2026-10-07T20:21:21.898000+00:00.",
      "date_published": "2026-10-07T20:21:21.898000+00:00",
      "_diff": {
        "model_id": "poolside/Laguna-S-2.1",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon Verified 49.7%",
        "source_url": "https://huggingface.co/poolside/Laguna-S-2.1/raw/main/README.md",
        "observed_at": "2026-10-07T20:21:21.898000+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "f6df016acf559621edb3",
      "url": "https://openmodeldrops.com/models/google/gemma-4-31B-it-assistant/",
      "title": "gemma-4-31B-it-assistant: Author reports Tau2 (average over 3) 76.9%",
      "content_text": "google/gemma-4-31B-it-assistant has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 76.9% (Gemma 4 31B). Source: https://huggingface.co/google/gemma-4-31B-it-assistant/raw/main/README.md. Observed at 2026-10-07T20:21:17.344339+00:00.",
      "date_published": "2026-10-07T20:21:17.344339+00:00",
      "_diff": {
        "model_id": "google/gemma-4-31B-it-assistant",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 76.9%",
        "source_url": "https://huggingface.co/google/gemma-4-31B-it-assistant/raw/main/README.md",
        "observed_at": "2026-10-07T20:21:17.344339+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "5ca3e3c58d06433a15d5",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-Next-80B-A3B-Thinking/",
      "title": "Qwen3-Next-80B-A3B-Thinking: Author reports BFCL-v3 72.0",
      "content_text": "Qwen/Qwen3-Next-80B-A3B-Thinking has author-reported evidence for \"Call tools and APIs\": Author reports BFCL-v3 72.0. Source: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking/raw/main/README.md. Observed at 2026-10-07T20:21:08.022739+00:00.",
      "date_published": "2026-10-07T20:21:08.022739+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL-v3 72.0",
        "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking/raw/main/README.md",
        "observed_at": "2026-10-07T20:21:08.022739+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "efae72ffae17860d58f5",
      "url": "https://openmodeldrops.com/models/google/gemma-4-12B/",
      "title": "gemma-4-12B: Author reports Tau2 (average over 3) 69.0%",
      "content_text": "google/gemma-4-12B has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 69.0% (Gemma 4 12B Unified). Source: https://huggingface.co/google/gemma-4-12B/raw/main/README.md. Observed at 2026-10-07T20:21:05.712743+00:00.",
      "date_published": "2026-10-07T20:21:05.712743+00:00",
      "_diff": {
        "model_id": "google/gemma-4-12B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 69.0%",
        "source_url": "https://huggingface.co/google/gemma-4-12B/raw/main/README.md",
        "observed_at": "2026-10-07T20:21:05.712743+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "d1f8e92f5735508d88a4",
      "url": "https://openmodeldrops.com/models/stepfun-ai/Step-3.7-Flash/",
      "title": "Step-3.7-Flash: Author reports Toolathlon 49.5",
      "content_text": "stepfun-ai/Step-3.7-Flash has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon 49.5. Source: https://huggingface.co/stepfun-ai/Step-3.7-Flash/raw/main/README.md. Observed at 2026-10-07T20:21:04.753951+00:00.",
      "date_published": "2026-10-07T20:21:04.753951+00:00",
      "_diff": {
        "model_id": "stepfun-ai/Step-3.7-Flash",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon 49.5",
        "source_url": "https://huggingface.co/stepfun-ai/Step-3.7-Flash/raw/main/README.md",
        "observed_at": "2026-10-07T20:21:04.753951+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "aaa96b3d47cb2d6ab288",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-30B-A3B-Thinking-2507/",
      "title": "Qwen3-30B-A3B-Thinking-2507: Author reports BFCL-v3 72.4",
      "content_text": "Qwen/Qwen3-30B-A3B-Thinking-2507 has author-reported evidence for \"Call tools and APIs\": Author reports BFCL-v3 72.4. Source: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/raw/main/README.md. Observed at 2026-10-07T20:20:57.251386+00:00.",
      "date_published": "2026-10-07T20:20:57.251386+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL-v3 72.4",
        "source_url": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/raw/main/README.md",
        "observed_at": "2026-10-07T20:20:57.251386+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "660adcb47235e163ed8c",
      "url": "https://openmodeldrops.com/models/XiaomiMiMo/MiMo-V2.6-Flash-RL/",
      "title": "MiMo-V2.6-Flash-RL: Author reports Toolathlon-Verified 73.6",
      "content_text": "XiaomiMiMo/MiMo-V2.6-Flash-RL has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon-Verified 73.6 (MiMo-V2.6 Flash). Source: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL/raw/main/README.md. Observed at 2026-10-07T20:20:56.547560+00:00.",
      "date_published": "2026-10-07T20:20:56.547560+00:00",
      "_diff": {
        "model_id": "XiaomiMiMo/MiMo-V2.6-Flash-RL",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon-Verified 73.6",
        "source_url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL/raw/main/README.md",
        "observed_at": "2026-10-07T20:20:56.547560+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "e0ee6314ae3bc7fc719b",
      "url": "https://openmodeldrops.com/models/google/gemma-4-E2B/",
      "title": "gemma-4-E2B: Author reports Tau2 (average over 3) 24.5%",
      "content_text": "google/gemma-4-E2B has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 24.5% (Gemma 4 E2B). Source: https://huggingface.co/google/gemma-4-E2B/raw/main/README.md. Observed at 2026-10-07T20:20:29.538589+00:00.",
      "date_published": "2026-10-07T20:20:29.538589+00:00",
      "_diff": {
        "model_id": "google/gemma-4-E2B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 24.5%",
        "source_url": "https://huggingface.co/google/gemma-4-E2B/raw/main/README.md",
        "observed_at": "2026-10-07T20:20:29.538589+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "cb9934167fd66aee44c7",
      "url": "https://openmodeldrops.com/models/HuggingFaceTB/SmolLM3-3B/",
      "title": "SmolLM3-3B: Author reports BFCL 92.3",
      "content_text": "HuggingFaceTB/SmolLM3-3B has author-reported evidence for \"Call tools and APIs\": Author reports BFCL 92.3 (Instruction Model, No Extended Thinking). Source: https://huggingface.co/HuggingFaceTB/SmolLM3-3B/raw/main/README.md. Observed at 2026-10-07T20:20:22.315403+00:00.",
      "date_published": "2026-10-07T20:20:22.315403+00:00",
      "_diff": {
        "model_id": "HuggingFaceTB/SmolLM3-3B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL 92.3",
        "source_url": "https://huggingface.co/HuggingFaceTB/SmolLM3-3B/raw/main/README.md",
        "observed_at": "2026-10-07T20:20:22.315403+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "0429d9eb98ec3f21c625",
      "url": "https://openmodeldrops.com/models/XiaomiMiMo/MiMo-V2.6-Pro-RL/",
      "title": "MiMo-V2.6-Pro-RL: Author reports Toolathlon-Verified 76.9",
      "content_text": "XiaomiMiMo/MiMo-V2.6-Pro-RL has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon-Verified 76.9 (MiMo-V2.6 Pro). Source: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/raw/main/README.md. Observed at 2026-10-07T20:20:12.212094+00:00.",
      "date_published": "2026-10-07T20:20:12.212094+00:00",
      "_diff": {
        "model_id": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon-Verified 76.9",
        "source_url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/raw/main/README.md",
        "observed_at": "2026-10-07T20:20:12.212094+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "c7184e40f971191ee489",
      "url": "https://openmodeldrops.com/models/google/gemma-4-26B-A4B/",
      "title": "gemma-4-26B-A4B: Author reports Tau2 (average over 3) 68.2%",
      "content_text": "google/gemma-4-26B-A4B has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 68.2% (Gemma 4 26B A4B). Source: https://huggingface.co/google/gemma-4-26B-A4B/raw/main/README.md. Observed at 2026-10-07T20:20:11.847069+00:00.",
      "date_published": "2026-10-07T20:20:11.847069+00:00",
      "_diff": {
        "model_id": "google/gemma-4-26B-A4B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 68.2%",
        "source_url": "https://huggingface.co/google/gemma-4-26B-A4B/raw/main/README.md",
        "observed_at": "2026-10-07T20:20:11.847069+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "ea601fbc83d584bc5418",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-235B-A22B-Thinking-2507/",
      "title": "Qwen3-235B-A22B-Thinking-2507: Author reports BFCL-v3 71.9",
      "content_text": "Qwen/Qwen3-235B-A22B-Thinking-2507 has author-reported evidence for \"Call tools and APIs\": Author reports BFCL-v3 71.9. Source: https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507/raw/main/README.md. Observed at 2026-10-07T20:20:04.754537+00:00.",
      "date_published": "2026-10-07T20:20:04.754537+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL-v3 71.9",
        "source_url": "https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507/raw/main/README.md",
        "observed_at": "2026-10-07T20:20:04.754537+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "0043aaefdc709efa9cf9",
      "url": "https://openmodeldrops.com/models/google/gemma-4-E4B/",
      "title": "gemma-4-E4B: Author reports Tau2 (average over 3) 42.2%",
      "content_text": "google/gemma-4-E4B has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 42.2% (Gemma 4 E4B). Source: https://huggingface.co/google/gemma-4-E4B/raw/main/README.md. Observed at 2026-10-07T20:19:55.830091+00:00.",
      "date_published": "2026-10-07T20:19:55.830091+00:00",
      "_diff": {
        "model_id": "google/gemma-4-E4B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 42.2%",
        "source_url": "https://huggingface.co/google/gemma-4-E4B/raw/main/README.md",
        "observed_at": "2026-10-07T20:19:55.830091+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "8fe4c5b8027cd9a366f9",
      "url": "https://openmodeldrops.com/models/nvidia/NVIDIA-Nemotron-Nano-9B-v2/",
      "title": "NVIDIA-Nemotron-Nano-9B-v2: Author reports BFCL v3 66.9%",
      "content_text": "nvidia/NVIDIA-Nemotron-Nano-9B-v2 has author-reported evidence for \"Call tools and APIs\": Author reports BFCL v3 66.9% (Reasoning On). Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2/raw/main/README.md. Observed at 2026-10-07T20:19:53.646336+00:00.",
      "date_published": "2026-10-07T20:19:53.646336+00:00",
      "_diff": {
        "model_id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL v3 66.9%",
        "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2/raw/main/README.md",
        "observed_at": "2026-10-07T20:19:53.646336+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "126e620cc122aa1d36be",
      "url": "https://openmodeldrops.com/models/google/diffusiongemma-26B-A4B-it/",
      "title": "diffusiongemma-26B-A4B-it: Author reports Tau2 (average over 3) 56.2%",
      "content_text": "google/diffusiongemma-26B-A4B-it has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 56.2% (DiffusionGemma 26B A4B). Source: https://huggingface.co/google/diffusiongemma-26B-A4B-it/raw/main/README.md. Observed at 2026-10-07T20:19:48.067859+00:00.",
      "date_published": "2026-10-07T20:19:48.067859+00:00",
      "_diff": {
        "model_id": "google/diffusiongemma-26B-A4B-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 56.2%",
        "source_url": "https://huggingface.co/google/diffusiongemma-26B-A4B-it/raw/main/README.md",
        "observed_at": "2026-10-07T20:19:48.067859+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "29797d374dfc3823cea5",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-4B-Thinking-2507/",
      "title": "Qwen3-4B-Thinking-2507: Author reports BFCL-v3 71.2",
      "content_text": "Qwen/Qwen3-4B-Thinking-2507 has author-reported evidence for \"Call tools and APIs\": Author reports BFCL-v3 71.2 (Qwen3-4B-Thinking-2507). Source: https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/raw/main/README.md. Observed at 2026-10-07T20:19:47.128419+00:00.",
      "date_published": "2026-10-07T20:19:47.128419+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-4B-Thinking-2507",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL-v3 71.2",
        "source_url": "https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/raw/main/README.md",
        "observed_at": "2026-10-07T20:19:47.128419+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "691430833dcb166e1867",
      "url": "https://openmodeldrops.com/models/google/gemma-4-31B/",
      "title": "gemma-4-31B: Author reports Tau2 (average over 3) 76.9%",
      "content_text": "google/gemma-4-31B has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 76.9% (Gemma 4 31B). Source: https://huggingface.co/google/gemma-4-31B/raw/main/README.md. Observed at 2026-10-07T20:19:22.456254+00:00.",
      "date_published": "2026-10-07T20:19:22.456254+00:00",
      "_diff": {
        "model_id": "google/gemma-4-31B",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 76.9%",
        "source_url": "https://huggingface.co/google/gemma-4-31B/raw/main/README.md",
        "observed_at": "2026-10-07T20:19:22.456254+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "19164443c2aae3d77b71",
      "url": "https://openmodeldrops.com/models/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp/",
      "title": "DeepSeek-V4-Flash-Vision-Exp: Author reports Toolathlon-Verified 75.9",
      "content_text": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon-Verified 75.9 (Text Agent Capabilities). Source: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp/raw/main/README.md. Observed at 2026-10-07T20:18:39.127206+00:00.",
      "date_published": "2026-10-07T20:18:39.127206+00:00",
      "_diff": {
        "model_id": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon-Verified 75.9",
        "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp/raw/main/README.md",
        "observed_at": "2026-10-07T20:18:39.127206+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "0143995815953530f599",
      "url": "https://openmodeldrops.com/models/google/gemma-4-E2B-it/",
      "title": "gemma-4-E2B-it: Author reports Tau2 (average over 3) 24.5%",
      "content_text": "google/gemma-4-E2B-it has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 24.5% (Gemma 4 E2B). Source: https://huggingface.co/google/gemma-4-E2B-it/raw/main/README.md. Observed at 2026-10-07T20:18:23.721758+00:00.",
      "date_published": "2026-10-07T20:18:23.721758+00:00",
      "_diff": {
        "model_id": "google/gemma-4-E2B-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 24.5%",
        "source_url": "https://huggingface.co/google/gemma-4-E2B-it/raw/main/README.md",
        "observed_at": "2026-10-07T20:18:23.721758+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "cfd18e901e06cbfd375d",
      "url": "https://openmodeldrops.com/models/google/gemma-4-12B-it/",
      "title": "gemma-4-12B-it: Author reports Tau2 (average over 3) 69.0%",
      "content_text": "google/gemma-4-12B-it has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 69.0% (Gemma 4 12B Unified). Source: https://huggingface.co/google/gemma-4-12B-it/raw/main/README.md. Observed at 2026-10-07T20:18:18.754019+00:00.",
      "date_published": "2026-10-07T20:18:18.754019+00:00",
      "_diff": {
        "model_id": "google/gemma-4-12B-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 69.0%",
        "source_url": "https://huggingface.co/google/gemma-4-12B-it/raw/main/README.md",
        "observed_at": "2026-10-07T20:18:18.754019+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "5acc686c5175d766d65c",
      "url": "https://openmodeldrops.com/models/deepseek-ai/DeepSeek-V4-Pro-0813/",
      "title": "DeepSeek-V4-Pro-0813: Author reports Toolathlon-Verified 74.1",
      "content_text": "deepseek-ai/DeepSeek-V4-Pro-0813 has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon-Verified 74.1. Source: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/raw/main/README.md. Observed at 2026-10-07T20:17:47.016485+00:00.",
      "date_published": "2026-10-07T20:17:47.016485+00:00",
      "_diff": {
        "model_id": "deepseek-ai/DeepSeek-V4-Pro-0813",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon-Verified 74.1",
        "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/raw/main/README.md",
        "observed_at": "2026-10-07T20:17:47.016485+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "25f25426d31095159e0d",
      "url": "https://openmodeldrops.com/models/google/gemma-4-E4B-it/",
      "title": "gemma-4-E4B-it: Author reports Tau2 (average over 3) 42.2%",
      "content_text": "google/gemma-4-E4B-it has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 42.2% (Gemma 4 E4B). Source: https://huggingface.co/google/gemma-4-E4B-it/raw/main/README.md. Observed at 2026-10-07T20:17:16.087842+00:00.",
      "date_published": "2026-10-07T20:17:16.087842+00:00",
      "_diff": {
        "model_id": "google/gemma-4-E4B-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 42.2%",
        "source_url": "https://huggingface.co/google/gemma-4-E4B-it/raw/main/README.md",
        "observed_at": "2026-10-07T20:17:16.087842+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "37d6b88e8e4ec666f456",
      "url": "https://openmodeldrops.com/models/deepseek-ai/DeepSeek-R1-0528/",
      "title": "DeepSeek-R1-0528: Author reports BFCL_v3_MultiTurn (Acc) 37.0",
      "content_text": "deepseek-ai/DeepSeek-R1-0528 has author-reported evidence for \"Call tools and APIs\": Author reports BFCL_v3_MultiTurn (Acc) 37.0 (DeepSeek R1 0528). Source: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/raw/main/README.md. Observed at 2026-10-07T20:16:50.849233+00:00.",
      "date_published": "2026-10-07T20:16:50.849233+00:00",
      "_diff": {
        "model_id": "deepseek-ai/DeepSeek-R1-0528",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL_v3_MultiTurn (Acc) 37.0",
        "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/raw/main/README.md",
        "observed_at": "2026-10-07T20:16:50.849233+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "3e4965651f87b2a2aa74",
      "url": "https://openmodeldrops.com/models/Qwen/Qwen3-Next-80B-A3B-Instruct/",
      "title": "Qwen3-Next-80B-A3B-Instruct: Author reports BFCL-v3 70.3",
      "content_text": "Qwen/Qwen3-Next-80B-A3B-Instruct has author-reported evidence for \"Call tools and APIs\": Author reports BFCL-v3 70.3. Source: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct/raw/main/README.md. Observed at 2026-10-07T20:16:39.354303+00:00.",
      "date_published": "2026-10-07T20:16:39.354303+00:00",
      "_diff": {
        "model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports BFCL-v3 70.3",
        "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct/raw/main/README.md",
        "observed_at": "2026-10-07T20:16:39.354303+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "3db168d9f2ca00f3c2bf",
      "url": "https://openmodeldrops.com/models/moonshotai/Kimi-K2.6/",
      "title": "Kimi-K2.6: Author reports Toolathlon 50.0",
      "content_text": "moonshotai/Kimi-K2.6 has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon 50.0 (Agentic). Source: https://huggingface.co/moonshotai/Kimi-K2.6/raw/main/README.md. Observed at 2026-10-07T20:16:34.543536+00:00.",
      "date_published": "2026-10-07T20:16:34.543536+00:00",
      "_diff": {
        "model_id": "moonshotai/Kimi-K2.6",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon 50.0",
        "source_url": "https://huggingface.co/moonshotai/Kimi-K2.6/raw/main/README.md",
        "observed_at": "2026-10-07T20:16:34.543536+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "e4b6ffea76a2f6e6fb4d",
      "url": "https://openmodeldrops.com/models/google/gemma-4-31B-it/",
      "title": "gemma-4-31B-it: Author reports Tau2 (average over 3) 76.9%",
      "content_text": "google/gemma-4-31B-it has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 76.9% (Gemma 4 31B). Source: https://huggingface.co/google/gemma-4-31B-it/raw/main/README.md. Observed at 2026-10-07T20:15:39.011299+00:00.",
      "date_published": "2026-10-07T20:15:39.011299+00:00",
      "_diff": {
        "model_id": "google/gemma-4-31B-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 76.9%",
        "source_url": "https://huggingface.co/google/gemma-4-31B-it/raw/main/README.md",
        "observed_at": "2026-10-07T20:15:39.011299+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "0d16b0e45a9ca9ffbada",
      "url": "https://openmodeldrops.com/models/zai-org/GLM-5.3/",
      "title": "GLM-5.3: Author reports Toolathlon Verified 73.0",
      "content_text": "zai-org/GLM-5.3 has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon Verified 73.0. Source: https://huggingface.co/zai-org/GLM-5.3/raw/main/README.md. Observed at 2026-10-07T20:15:39.010938+00:00.",
      "date_published": "2026-10-07T20:15:39.010938+00:00",
      "_diff": {
        "model_id": "zai-org/GLM-5.3",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon Verified 73.0",
        "source_url": "https://huggingface.co/zai-org/GLM-5.3/raw/main/README.md",
        "observed_at": "2026-10-07T20:15:39.010938+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "29bb96866c09c1a13a85",
      "url": "https://openmodeldrops.com/models/google/gemma-4-26B-A4B-it/",
      "title": "gemma-4-26B-A4B-it: Author reports Tau2 (average over 3) 68.2%",
      "content_text": "google/gemma-4-26B-A4B-it has author-reported evidence for \"Call tools and APIs\": Author reports Tau2 (average over 3) 68.2% (Gemma 4 26B A4B). Source: https://huggingface.co/google/gemma-4-26B-A4B-it/raw/main/README.md. Observed at 2026-10-07T20:14:26.358568+00:00.",
      "date_published": "2026-10-07T20:14:26.358568+00:00",
      "_diff": {
        "model_id": "google/gemma-4-26B-A4B-it",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Tau2 (average over 3) 68.2%",
        "source_url": "https://huggingface.co/google/gemma-4-26B-A4B-it/raw/main/README.md",
        "observed_at": "2026-10-07T20:14:26.358568+00:00",
        "kind": "usecase"
      }
    },
    {
      "id": "322e1c286ea3b7505511",
      "url": "https://openmodeldrops.com/models/deepseek-ai/DeepSeek-V4-Flash-0731/",
      "title": "DeepSeek-V4-Flash-0731: Author reports Toolathlon-Verified 70.3",
      "content_text": "deepseek-ai/DeepSeek-V4-Flash-0731 has author-reported evidence for \"Call tools and APIs\": Author reports Toolathlon-Verified 70.3. Source: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/raw/main/README.md. Observed at 2026-10-07T20:12:46.680562+00:00.",
      "date_published": "2026-10-07T20:12:46.680562+00:00",
      "_diff": {
        "model_id": "deepseek-ai/DeepSeek-V4-Flash-0731",
        "field": "use_case:tool-use",
        "old": null,
        "new": "Author reports Toolathlon-Verified 70.3",
        "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/raw/main/README.md",
        "observed_at": "2026-10-07T20:12:46.680562+00:00",
        "kind": "usecase"
      }
    }
  ]
}