{
  "schema_version": "1.0",
  "id": "archive:https://huggingface.co/blog/eee-community-evals",
  "slug": "eee-community-evals-0d7cned",
  "url": "https://feed7.dev/p/eee-community-evals-0d7cned",
  "title": "Featuring Every Eval Ever Results on Hugging Face Model Pages",
  "why_included": "Every Eval Ever's ~229k benchmark results across 22k+ models now cross-post to Hugging Face model pages with attribution — one less reason for the same model to show two different MMLU scores.",
  "summary": "**The gist** Hugging Face and the EvalEval Coalition made **Every Eval Ever** interoperable with HF Community Evals: a converter maps EEE's JSON into HF's YAML and opens PRs against model pages. The datastore holds about **229,000 results** across **22,000+ models** and 2,200 benchmarks pulled from 31 reporting formats; four benchmarks are wired up so far: **MMLU-Pro, GPQA, HLE, and GSM8K**.",
  "practical_implication": "**Why it matters** Model selection today means trusting whichever score a vendor or leaderboard reports — **LLaMA 65B** has been listed at both **63.7 and 48.8** on MMLU. Attributed, aggregated results on the model page give you a sanity check before swapping the model behind your agents, from a corpus that would cost **hundreds of thousands of dollars** to reproduce.",
  "agent_context": "**The gist** Hugging Face and the EvalEval Coalition made **Every Eval Ever** interoperable with HF Community Evals: a converter maps EEE's JSON into HF's YAML and opens PRs against model pages. The datastore holds about **229,000 results** across **22,000+ models** and 2,200 benchmarks pulled from 31 reporting formats; four benchmarks are wired up so far: **MMLU-Pro, GPQA, HLE, and GSM8K**.\n\n**Why it matters** Model selection today means trusting whichever score a vendor or leaderboard reports — **LLaMA 65B** has been listed at both **63.7 and 48.8** on MMLU. Attributed, aggregated results on the model page give you a sanity check before swapping the model behind your agents, from a corpus that would cost **hundreds of thousands of dollars** to reproduce.\n\n**Watch out** Coverage is thin: only **four benchmarks** convert today with **no stated timeline** for more, and aggregation surfaces conflicting scores without resolving which number is right.",
  "source": {
    "name": "huggingface.co",
    "url": "https://huggingface.co/blog/eee-community-evals",
    "published_at": null
  },
  "source_class": "blog_post",
  "content_type": "Source",
  "layer": "benchmark",
  "domains": [],
  "topics": [
    "benchmark-integrity",
    "model-selection"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Coverage is thin: only **four benchmarks** convert today with **no stated timeline** for more, and aggregation surfaces conflicting scores without resolving which number is right."
  ],
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/eee-community-evals-0d7cned",
    "json": "https://feed7.dev/p/eee-community-evals-0d7cned.json",
    "markdown": "https://feed7.dev/p/eee-community-evals-0d7cned.md"
  }
}