{"criteriaVersion":"1.0","evaluations":[{"slug":"adf","name":"ADF","vendor":"Christian Balevski","score":66.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/adf.json","run":"/runs/2026-09-30-v1.json"},{"slug":"aider","name":"Aider","vendor":"Aider-AI (Paul Gauthier)","score":63.9,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/aider.json","run":"/runs/2026-09-30-v1.json"},{"slug":"pi","name":"Pi","vendor":"Earendil Inc.","score":61.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/pi.json","run":"/runs/2026-09-30-v1.json"},{"slug":"zeroclaw","name":"ZeroClaw","vendor":"ZeroClaw Labs","score":61.4,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/zeroclaw.json","run":"/runs/2026-09-30-v1.json"},{"slug":"openclaw","name":"OpenClaw","vendor":"OpenClaw Foundation","score":56.3,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/openclaw.json","run":"/runs/2026-09-30-v1.json"},{"slug":"open-webui","name":"Open WebUI","vendor":"Open WebUI Inc.","score":55.1,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/open-webui.json","run":"/runs/2026-09-30-v1.json"},{"slug":"opencode","name":"OpenCode","vendor":"Anomaly (formerly SST)","score":51.9,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/opencode.json","run":"/runs/2026-09-30-v1.json"},{"slug":"nanobot","name":"nanobot","vendor":"HKUDS","score":50.8,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/nanobot.json","run":"/runs/2026-09-30-v1.json"},{"slug":"goose","name":"goose","vendor":"Agentic AI Foundation","score":50.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/goose.json","run":"/runs/2026-09-30-v1.json"},{"slug":"openhands","name":"OpenHands","vendor":"OpenHands (All Hands AI)","score":46.5,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/openhands.json","run":"/runs/2026-09-30-v1.json"},{"slug":"anythingllm","name":"AnythingLLM","vendor":"Mintplex Labs","score":45.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/anythingllm.json","run":"/runs/2026-09-30-v1.json"},{"slug":"deepseek-harness","name":"DeepSeek Harness","vendor":"DeepSeek (Hangzhou DeepSeek Artificial Intelligence)","score":41.5,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/deepseek-harness.json","run":"/runs/2026-09-30-v1.json"},{"slug":"open-interpreter","name":"Open Interpreter","vendor":"Open Interpreter","score":41,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/open-interpreter.json","run":"/runs/2026-09-30-v1.json"},{"slug":"hermes-agent","name":"Hermes Agent","vendor":"Nous Research","score":40.4,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/hermes-agent.json","run":"/runs/2026-09-30-v1.json"},{"slug":"openai-codex","name":"OpenAI Codex","vendor":"OpenAI","score":40.4,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/openai-codex.json","run":"/runs/2026-09-30-v1.json"},{"slug":"gemini-cli","name":"Gemini CLI","vendor":"Google","score":39.2,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/gemini-cli.json","run":"/runs/2026-09-30-v1.json"},{"slug":"cline","name":"Cline","vendor":"Cline Bot Inc.","score":37.6,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/cline.json","run":"/runs/2026-09-30-v1.json"},{"slug":"github-copilot","name":"GitHub Copilot","vendor":"GitHub (Microsoft)","score":37.4,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/github-copilot.json","run":"/runs/2026-09-30-v1.json"},{"slug":"claude-code","name":"Claude Code","vendor":"Anthropic","score":35.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/claude-code.json","run":"/runs/2026-09-30-v1.json"},{"slug":"lobehub","name":"LobeHub","vendor":"LobeHub LLC","score":31.8,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/lobehub.json","run":"/runs/2026-09-30-v1.json"},{"slug":"cursor","name":"Cursor","vendor":"Anysphere","score":26.9,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/cursor.json","run":"/runs/2026-09-30-v1.json"},{"slug":"microsoft-copilot-cowork","name":"Microsoft Copilot Cowork","vendor":"Microsoft","score":23.6,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/microsoft-copilot-cowork.json","run":"/runs/2026-09-30-v1.json"},{"slug":"autogpt","name":"AutoGPT Platform","vendor":"Significant Gravitas","score":22.9,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/autogpt.json","run":"/runs/2026-09-30-v1.json"},{"slug":"chatgpt","name":"ChatGPT","vendor":"OpenAI","score":20.6,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/chatgpt.json","run":"/runs/2026-09-30-v1.json"},{"slug":"devin","name":"Devin","vendor":"Cognition","score":19.9,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/devin.json","run":"/runs/2026-09-30-v1.json"},{"slug":"letta","name":"Letta","vendor":"Letta, Inc.","score":19,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/letta.json","run":"/runs/2026-09-30-v1.json"},{"slug":"grok","name":"Grok","vendor":"xAI","score":18.5,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/grok.json","run":"/runs/2026-09-30-v1.json"},{"slug":"lovable","name":"Lovable","vendor":"Lovable","score":18.5,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/lovable.json","run":"/runs/2026-09-30-v1.json"},{"slug":"mistral-vibe","name":"Mistral Vibe","vendor":"Mistral AI","score":18.5,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/mistral-vibe.json","run":"/runs/2026-09-30-v1.json"},{"slug":"gemini","name":"Gemini","vendor":"Google","score":18.1,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/gemini.json","run":"/runs/2026-09-30-v1.json"},{"slug":"meta-muse","name":"Meta Muse","vendor":"Meta","score":17.5,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/meta-muse.json","run":"/runs/2026-09-30-v1.json"},{"slug":"chatgpt-atlas","name":"ChatGPT Atlas","vendor":"OpenAI","score":15.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/chatgpt-atlas.json","run":"/runs/2026-09-30-v1.json"},{"slug":"doubao","name":"Doubao","vendor":"ByteDance","score":15.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/doubao.json","run":"/runs/2026-09-30-v1.json"},{"slug":"manus","name":"Manus","vendor":"Manus","score":15.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/manus.json","run":"/runs/2026-09-30-v1.json"},{"slug":"replit-agent","name":"Replit Agent","vendor":"Replit","score":15.4,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/replit-agent.json","run":"/runs/2026-09-30-v1.json"},{"slug":"claude-cowork","name":"Claude Cowork","vendor":"Anthropic","score":15,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/claude-cowork.json","run":"/runs/2026-09-30-v1.json"},{"slug":"grok-bot","name":"Grok Bot","vendor":"xAI","score":14,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/grok-bot.json","run":"/runs/2026-09-30-v1.json"},{"slug":"alexa-plus","name":"Alexa+","vendor":"Amazon","score":13.6,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/alexa-plus.json","run":"/runs/2026-09-30-v1.json"},{"slug":"gemini-spark","name":"Gemini Spark","vendor":"Google","score":12.9,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/gemini-spark.json","run":"/runs/2026-09-30-v1.json"},{"slug":"perplexity-comet","name":"Perplexity Comet","vendor":"Perplexity AI, Inc.","score":11.3,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/perplexity-comet.json","run":"/runs/2026-09-30-v1.json"},{"slug":"claude","name":"Claude","vendor":"Anthropic","score":11.2,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/claude.json","run":"/runs/2026-09-30-v1.json"},{"slug":"microsoft-copilot","name":"Microsoft Copilot","vendor":"Microsoft","score":10.7,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/microsoft-copilot.json","run":"/runs/2026-09-30-v1.json"},{"slug":"genspark","name":"Genspark","vendor":"MainFunc Inc. (Genspark)","score":9.6,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/genspark.json","run":"/runs/2026-09-30-v1.json"},{"slug":"meta-ai","name":"Meta AI","vendor":"Meta Platforms","score":9.6,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/meta-ai.json","run":"/runs/2026-09-30-v1.json"},{"slug":"apple-siri-ai","name":"Siri","vendor":"Apple","score":9.6,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/apple-siri-ai.json","run":"/runs/2026-09-30-v1.json"},{"slug":"openai-dots","name":"OpenAI Dots","vendor":"OpenAI","score":9.2,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/openai-dots.json","run":"/runs/2026-09-30-v1.json"},{"slug":"deepseek","name":"DeepSeek","vendor":"DeepSeek (Hangzhou DeepSeek Artificial Intelligence)","score":7.9,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/deepseek.json","run":"/runs/2026-09-30-v1.json"},{"slug":"google-cc","name":"Google CC","vendor":"Google (Google Labs)","score":6.3,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/google-cc.json","run":"/runs/2026-09-30-v1.json"},{"slug":"instinct","name":"Instinct","vendor":"Spear Street Technology, Inc.","score":3.1,"criteriaVersion":"1.0","evaluatedAt":"2026-09-30","url":"/evaluations/instinct.json","run":"/runs/2026-09-30-v1.json"}]}