MTEB Leaderboard
📊
7.77k
Embedding Leaderboard
Deep Research
Recherche, RAG, web, long-context
-
-
Q2D-Web Leaderboard
🔎22Q2D-Web: large-scale first-stage retrieval for agentic RAG
-
LFM2.5 Edge Research Agent
🔬83Run an on-device LFM2.5 research agent with WebGPU
-
Multi-agent Deep-research System
👋35A multi-agent system for deep research on a topic
-
AgenticRAG
🌖99Answer questions using web, weather, and dataset tools
-
google/simpleqa-verified
Viewer • Updated • 1k • 9.99k • 56 -
livebench/language
Viewer • Updated • 190 • 5.25k • 1 -
livebench/coding
Viewer • Updated • 128 • 6.48k • 14 -
livebench/reasoning
Viewer • Updated • 200 • 7.28k • 20 -
livebench/math
Viewer • Updated • 368 • 16.1k • 3 -
livebench/instruction_following
Viewer • Updated • 400 • 10.5k • 8 -
livebench/data_analysis
Viewer • Updated • 150 • 28.2k • 8 -
livebench/model_answer
Viewer • Updated • 93.7k • 808 • 1 -
livebench/model_judgment
Viewer • Updated • 60.4k • 3.35k • 2 -
livebench/liveswebench
Viewer • Updated • 53 • 150 • 3 -
livebench/liveswebench-patches
Viewer • Updated • 1 • 222 • 1 -
Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 6.55M • • 20.1k -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 2.25M • • 859 -
Qwen/Qwen3-Reranker-8B
Text Ranking • 8B • Updated • 75.1k • 298