Model × Framework Matrix

CRR scores at every model-framework intersection, derived from agent evaluations. Click any cell to see the agent detail.

4 of 66 baselines evaluated

Model	AutoGen	CrewAI	LangGraph	OpenAI Agents SDK	Raw FC	Smolagents
Claude Opus 4.6	—	—	—	—	—	—
Claude Sonnet 4.6	—	—	—	—	73.3	—
DeepSeek V3.2	—	—	—	—	65.4	—
Gemini 3 Flash	—	—	—	—	—	—
Gemini 3.1 Pro	—	—	—	—	—	—
GPT-5.4	—	—	—	—	67.7	—
GPT-5.4 Pro	—	—	—	—	—	—
Grok 4.20 Beta	—	—	—	—	65.5	—
Llama 4 Maverick	—	—	—	—	—	—
Mistral Large	—	—	—	—	—	—
Qwen 3.5	—	—	—	—	—	—

Benchmark your agent against real scenarios. Any framework — Anthropic, OpenAI, LangGraph, or raw HTTP.

pip install crtf · 30-line quickstart · Free during beta