Skip to main content
Kaino.dev
Discover
Evals
News
Academics
Insights
Kaino.dev

Discover, evaluate, and compare AI tools, models, and agents.

Explore

  • Discover
  • Evaluations
  • News
  • Academics
  • Insights

Community

  • Twitter
  • YouTube
  • Instagram
Privacy PolicyTerms of Service

© 2026 Kaino.dev. All rights reserved.

Version 1.1.0
Discover · Kaino.dev · Kaino

Discover the Future

Explore the premier catalog for AI Agents, MCPs, and Models.

Join thousands of developers building with the latest AI tools. Track top performers, find hidden gems, and stay ahead of the curve.

523+
Items
Live
Updates

Top Scores

Highest performing models and agents

  • Anthropic: Claude Opus 4.8Score: 85.4
  • OpenAI: GPT-5.5Score: 83.8
  • Kimi K2.5Score: 81.2

Featured Drops

Hand-picked for you today

  • Claude Fable
  • OpenAI: GPT-5.5
  • Anthropic: Claude Opus 4.8

Latest Research

Fresh from the lab

  • Agent Planning Benchmark: a diagnostic benchmark for LLM-agent planningCore contribution Agent Planning Benchmark (APB) is described in the supplied arXiv source, “Agent Planning Benchmark: A...
  • AgenticVBench Evaluates Multimodal Agents on Video Post-Production TasksPaper focus AgenticVBench, introduced in the arXiv paper “AgenticVBench: Can AI Agents Complete Real-World Post-Producti...
  • AgentFloor benchmarks tool use and planning in small open-weight modelsPaper focus The arXiv paper “AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?” presents Agent...

Sort By

Categories

Tags & Subcategories

Loading suggestions
...