LLM intelligence hub

Track the frontier of LLMs without losing the evidence.

EvalKit brings public leaderboards, model profiles, benchmark guides, and curated LLM news into one citation-first workspace.

Leaderboard rows464
Model profiles410
Public sources8
Verified claims0

Current leaders

Start with the models people are already comparing.

Open full explorer →

LLM news

Curated releases, research, and benchmark shifts.

Read news →

AI agents now have a place to snitch

The AI Contact Hotline is designed to be a discreet place where agents that have witnessed misbehavior can tip off authorities.

TechCrunch AISource

Bypassing inference bottlenecks: Accelerating complex AI search with Retrieve-for-Train

Algorithms & Theory

Google ResearchSource

Former TikTok execs built an app that uses AI to teach you how to pose for a photo

Essentially a camera app, Superpose analyzes selfies or photos and generates four potential poses using AI.

TechCrunch AISource

Meta expands subscription push with new AI-focused plans

Meta One bundles expanded access to the company’s AI tools with premium features across Facebook, Instagram, and WhatsApp.

TechCrunch AISource

Benchmark guide

Read scores like a product decision, not a scoreboard.

Open guide →

Trust policy

No fake “tested by us” claims.

Public rows are labeled as replicated public-source data or editorial context. “Verified by EvalKit” stays at 0 until there is real run evidence attached.

Read citation policy