No AI agent exceeds 12% on SemiAnalysis real-world work benchmark
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
SemiAnalysis tested AI agents on 206 simulated professional tasks across 11 fields. Claude Opus 5.5 led with 12%, followed by Gemini 4 Carbon at 10.9% and GPT-6 Astra at 9.6%; no model fully solved a finance or legal task. Critics questioned the small task counts and uneven testing conditions.
Continue in the app — vote & join in ➔Source: The Decoder (AI) · via ahirlevel.hu