AI Model Accuracy

Based on community expert verification. Each AI answer is checked and rated correct, incorrect, or partially correct.

280
Questions checked
2
Correct
5
Partially correct
266
Incorrect
ChatGPT74 questions · 68 verdicts
✓ 1 correct (1%)△ 2 partial (3%)✗ 65 incorrect (96%)
Gemini14 questions · 14 verdicts
✓ 0 correct (0%)△ 1 partial (7%)✗ 13 incorrect (93%)
ChatGPT (OpenAI)9 questions · 9 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 9 incorrect (100%)
Grok8 questions · 7 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 7 incorrect (100%)
Unidentified AI tool6 questions · 6 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 6 incorrect (100%)
AI chatbots5 questions · 5 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 5 incorrect (100%)
Google AI Overviews5 questions · 5 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 5 incorrect (100%)
AI coding assistants5 questions · 5 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 5 incorrect (100%)
Perplexity5 questions · 6 verdicts
✓ 0 correct (0%)△ 1 partial (17%)✗ 5 incorrect (83%)
Claude5 questions · 4 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 4 incorrect (100%)
Multiple AI chatbots4 questions · 4 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 4 incorrect (100%)
DeepSeek4 questions · 4 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 4 incorrect (100%)
Google Gemini3 questions · 3 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 3 incorrect (100%)
AI chatbot3 questions · 3 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 3 incorrect (100%)
Google3 questions · 3 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 3 incorrect (100%)
OpenAI3 questions · 3 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 3 incorrect (100%)
ChatGPT, Gemini, Claude3 questions · 3 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 3 incorrect (100%)
ChatGPT, Gemini and Perplexity2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
Grok (xAI)2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
AI coding agents2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
ChatGPT, Claude2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
ChatGPT, Gemini2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
ChatGPT, Gemini, Grok2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
AI search engines2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
Google AI Overview2 questions · 2 verdicts
✓ 0 correct (0%)△ 0 partial (0%)✗ 2 incorrect (100%)
ChatGPT, Gemini and Google AI Overview1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Google Antigravity (Gemini 3)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Google AI Mode1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Gemini 3.7 Flash1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Google Gemini (coding assistant)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
OpenAI agents1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unidentified generative AI tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT and Gemini1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unidentified AI legal research tools1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Irys (AI legal research tool)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI medical scribes (ambient transcription)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Claude and Gemini1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Google AI search tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Workday AI hiring tools1 question · 1 verdict
✓ 0 correct (0%)△ 1 partial (100%)✗ 0 incorrect (0%)
AI claims-review systems1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unidentified generative AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI farming app1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Anthropic Claude AI agent1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI deepfake video and image generators1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unidentified internal AI tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Character.AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Gemini, Claude, Copilot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Internal Amazon AI agent1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI mushroom identification apps1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Newsroom AI summarisation tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI travel chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Delta Concierge1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Canada Revenue Agency AI chatbot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
United Airlines AI chatbot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Microsoft Copilot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI-generated lawyer avatars1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Claude, Copilot, Gemini, Grok1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
New York City MyCity chatbot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Microsoft Copilot and Gemini1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
College support AI chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Maestro College AI instructor1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Verizon 'Ask Verizon' AI assistant1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Aesthetic clinic website AI chatbot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Generative AI (unnamed LLM)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Google Gemini, ChatGPT, Claude, Meta AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
LLM-based diagnostic AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Machine-learning life-detection system1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Commercial RLHF-trained chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Generative AI research tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
13 major LLMs1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Five most-used free AI chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI image generators1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI chatbots (multi-model test)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI chatbots (Which? test)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Anthropic1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
LLM chatbot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Multiple (Gemini, ChatGPT, Grok)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
GPT-4o, Meta models, Mistral, Alibaba Qwen1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
OpenAI GPT series, Anthropic Claude, Meta Llama1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unspecified AI tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Generative AI tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
GPT-5, Gemini, Claude1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
StepFun1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI Chatbot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
GitHub Copilot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
11 leading AI systems1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Claude, Gemini1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI travel planner1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Gemini, Claude (off-the-shelf LLMs)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT 51 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT Health (OpenAI)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Autonomous AI agents1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Aavegotchi1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI news-verification chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI translation tools1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
LLM chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Veo1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unidentified AI chatbot1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unspecified AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Court AI systems1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
General-purpose LLMs1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Ford automated quality / AI systems1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ICE AI screening tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI medical scribes1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI legal drafting tool (undisclosed)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Clearview AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Grok, Gemini1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
OpenAI / Google1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Google AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Gemini, Copilot, Meta AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI photo-based calorie apps1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Various LLMs (ChatGPT, Claude, Gemini)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Gemini, Grok, Meta AI, DeepSeek1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
LLMs1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Unidentified AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI Chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
OpenAI (GPT-4), Anthropic (Claude 3 Opus), Meta (Llama 3)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT (GPT-4)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
GPT-4, Claude, Gemini1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Claude (Anthropic)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Business Insider1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
ChatGPT, Gemini, Claude, various AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
DeepSeek, Mistral, NOVA AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Multiple (ChatGPT, Claude, Copilot, DeepSeek, Gemini, Meta AI, Perplexity)1 question · 1 verdict
✓ 1 correct (100%)△ 0 partial (0%)✗ 0 incorrect (0%)
AI Chatbots (ChatGPT, Claude, various)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
First Draft / AI Legal Document Tool1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Multiple AI coding tools (Cursor, Copilot, Claude Code)1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
AI Customer Service Chatbots1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Cursor AI1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)
Various AI tools1 question · 1 verdict
✓ 0 correct (0%)△ 0 partial (0%)✗ 1 incorrect (100%)

Data updated continuously as experts submit new verdicts.