10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 425 ms
agentrecord
- LLM leaderboards
Live arena rankings (text/code/agent/document/vision/search) with rank deltas, context length and pricing e.g. best coding model right now e.g. which models climbed this week
- LLM leaderboards
- 2LLM Router MCPfound in code, not yet checkedno passport yet
- route_prompt
Routes a coding prompt to the best LLM (Claude, Gemini, GPT-4o) based on task type. Automatically classifies the task and selects the cheapest/most capable model.
- route_prompt
modelrecord
- openai/gpt-5.1
The best model for coding and agentic tasks with configurable reasoning effort.
- openai/gpt-5.1
- 4local_llm_benchfound in code, not yet checkedno passport yet
MCP serverillia-piskurov/local_llm_bench
- get_leaderboard
Full ranking of models by quality — all benchmarks, averages, rankings.
- get_leaderboard
modelrecord
- openai/gpt-5.2
The best model for coding and agentic tasks across industries
- openai/gpt-5.2
modelrecord
- meta/codellama-34b
A 34 billion parameter Llama tuned for coding and conversation
- meta/codellama-34b
- 7gembots-arenafound in code, not yet checkedno passport yet
MCP serveravnikulin35/gembots-arena
- get_model_rankings
Get AI model rankings by prediction accuracy and ELO rating. Shows how 14+ LLMs (GPT-4, Claude, Gemini, Llama, Mistral, etc.) perform at crypto price prediction.
- get_model_rankings
modelrecord
- meta/codellama-7b
A 7 billion parameter Llama tuned for coding and conversation
- meta/codellama-7b
modelrecord
- meta/codellama-34b-instruct
A 34 billion parameter Llama tuned for coding and conversation
- meta/codellama-34b-instruct
modelrecord
- meta/codellama-70b-instruct
A 70 billion parameter Llama tuned for coding and conversation
- meta/codellama-70b-instruct
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.