skills.rest
bianhaifeng789-hue
bianhaifeng789-hueCOMMUNITY
Explore all skills by this author →
GitHub

mteb-leaderboard

Retrieve and validate embedding model rankings from MTEB and HuggingFace leaderboards.

Updated Apr 14, 2026
Search Tags:#embeddings#benchmarking#model-selection#huggingface#data-validation#leaderboard#mteb
One-click install
npx skills add https://github.com/bianhaifeng789-hue/openclaw-config --skill mteb-leaderboard-bianhaifeng789-hue
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mteb-leaderboard
Source: https://github.com/bianhaifeng789-hue/openclaw-config/tree/main/skills/tb2/mteb-leaderboard
Command: npx skills add https://github.com/bianhaifeng789-hue/openclaw-config --skill mteb-leaderboard-bianhaifeng789-hue

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps locate authoritative, current rankings and benchmark results for embedding models (MTEB, HuggingFace leaderboards, and related embedding benchmarks), resolving issues caused by interactive pages, outdated papers, or missing timestamps.

Core Features & Use Cases

  • Authoritative source discovery: Prioritize official leaderboard pages, GitHub data repositories, and API/JSON endpoints for canonical results.
  • Temporal validation: Check last-updated timestamps and explicitly handle date-constrained queries (for example, "as of August 2025").
  • Robust access methods: Extract raw CSV/JSON endpoints, use Spaces/Gradio APIs, or fall back to repository artifacts and Wayback Machine snapshots when UIs are interactive.
  • Eligibility and sanity checks: Verify model names, ranking eligibility, and cross-reference multiple sources to document discrepancies and provenance.
  • Use case: Report the top MTEB model for a specified date with score, evaluation split, and the timestamped data source.

Quick Start

Find the top-ranked model on the MTEB leaderboard as of August 2025 and provide its score, evaluation split, and a timestamped source link.

Frequently Asked Questions about mteb-leaderboard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find the top-ranked embedding models on the MTEB leaderboard as of a specific date?▼

To find top embedding models on the MTEB leaderboard by date, you retrieve raw JSON/CSV endpoints or API data, validate timestamps, and cross-reference sources to report the model score, evaluation split, and timestamped link.

What is the best way to get current HuggingFace embedding benchmark results when the interactive UI is unavailable?▼

The best way to get HuggingFace embedding benchmark results is to extract raw CSV/JSON endpoints, use Spaces/Gradio APIs, or fall back to repository artifacts and Wayback Machine snapshots when interactive UIs are inaccessible.

Can I validate model eligibility and exact naming when checking multiple embedding leaderboards?▼

Yes, you can validate model eligibility and exact naming by cross-referencing multiple leaderboard sources, checking authoritative repository data, and documenting any discrepancies and provenance found during the validation process.

Does retrieving MTEB benchmark data require specific API endpoints or can I use static files?▼

Retrieving MTEB benchmark data does not require specific API endpoints exclusively; you can apply robust access methods to extract raw CSV/JSON files, utilize Gradio APIs, or use static repository artifacts for canonical results.

Why do my embedding model rankings show discrepancies across different benchmark sources?▼

Embedding model rankings show discrepancies across benchmark sources due to outdated papers, missing timestamps, or varying evaluation splits, requiring cross-referencing multiple sources and temporal validation to document provenance.

Related Skills

Explore More Data & Analytics Skills→
Andrew-GirgisAndrew-Girgis

huggingface-best

Recommend top HuggingFace models by benchmark scores and device constraints.

Community
Advanced
letta-ailetta-ai
134

mteb-retrieve

Encode documents and queries with sentence-transformers, compute cosine similarities, and retrieve top-k results.

Official
Advanced
lazyFrogLOLlazyFrogLOL
127

mteb-leaderboard

Locate and verify MTEB leaderboard standings for embedding models.

Community
Intermediate
dawsonblockdawsonblock

github-wayback-recovery

Recover deleted GitHub content from Wayback Machine and CDX API snapshots.

Community
Advanced