OpenRouter Models Leaderboard: Adoption, Spend, Price and Context | CodeSOTA | CodeSOTA

Source: original

Codesota.Open SOTA registry

TasksModalitiesBenchmarksOpennessRL EnvsModelsRecent PapersOCR

APISign inTTS Elo ->

Menu

§ Agentic · OpenRouter models

Model rankings are refreshing.

The latest OpenRouter snapshot (2026-06-08) has no app-level detail yet, so per-model adoption can’t be computed. Check back shortly.

CodeSOTA.

A stricter benchmark registry for the agent era

Built in public from Warsaw open JSON · rankings stay earned

Codesota.

CodeSOTA maps AI capabilities to dated, sourced benchmark evidence — readable by humans, callable by agents.

Built in public from Warsaw · open JSON · rankings stay earned

Submit a score ↵Try /api/sota →

Registry

• Tasks
• Benchmarks
• Models
• Recent Papers
• Leaderboards
• Benchmark Lineages
• Methodology
• Submit a score

Capability Areas

• Language & Knowledge
• Vision & Documents
• Audio & Speech
• Multimodal Media
• Code & Software Engineering
• Agents & Tool Use
• Structured Data & Forecasting
• Robotics, Control & RL
• Science, Medicine & Industry

Deep Verticals

• OCR & Document AI
• Polish OCR
• Polish LLM
• Speech-to-Text
• Text-to-Speech
• Text Embeddings / MTEB
• Code Generation
• Agent Benchmarks
• Industrial Inspection
• Medical AI

Developer / Data

• /api/sota
• API schema
• Open JSON registry
• Data snapshots
• GitHub
• Report issue ↗
• Activity Log
• Changelog

Learn

• Guides
• Explainers
• Academy
• AI Model News
• Recent paper scan
• Papers with Code Story
• Research Challenges
• Data Flywheel

CodeSOTA

• About
• Cited by
• Advertise
• Consulting
• Praktyki
• Discord
• Get updates
• Privacy