{"slug": "gpt-and-claude-failed-bridgewater-s-finance-tests-because-the-right-answers-were", "title": "GPT and Claude failed Bridgewater's finance tests because the right answers were never public", "summary": "Bridgewater Associates and Thinking Machines Lab fine-tuned a Qwen3-235B model for financial tasks, achieving 84.7% accuracy and outperforming GPT, Claude, and Gemini at roughly one-fourteenth the cost. The results have not been independently verified.", "body_md": "Bridgewater and Thinking Machines Lab—the startup from former OpenAI CTO Mira Murati—have fine-tuned a Qwen3-235B model for financial tasks. According to their own testing, the model hits 84.7 percent accuracy, beating Gemini, Claude, and GPT at roughly one-fourteenth of the cost. The numbers haven't been verified by anyone outside the two companies, though.\n\nThe article [GPT and Claude failed Bridgewater's finance tests because the right answers were never public](https://the-decoder.com/gpt-and-claude-failed-bridgewaters-finance-tests-because-the-right-answers-were-never-public/) appeared first on [The Decoder](https://the-decoder.com).", "url": "https://wpnews.pro/news/gpt-and-claude-failed-bridgewater-s-finance-tests-because-the-right-answers-were", "canonical_source": "https://the-decoder.com/gpt-and-claude-failed-bridgewaters-finance-tests-because-the-right-answers-were-never-public/", "published_at": "2026-07-03 11:16:42+00:00", "updated_at": "2026-07-04 07:27:15.789234+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "ai-startups", "ai-products"], "entities": ["Bridgewater Associates", "Thinking Machines Lab", "Mira Murati", "OpenAI", "Qwen3-235B", "GPT", "Claude", "Gemini"], "alternates": {"html": "https://wpnews.pro/news/gpt-and-claude-failed-bridgewater-s-finance-tests-because-the-right-answers-were", "markdown": "https://wpnews.pro/news/gpt-and-claude-failed-bridgewater-s-finance-tests-because-the-right-answers-were.md", "text": "https://wpnews.pro/news/gpt-and-claude-failed-bridgewater-s-finance-tests-because-the-right-answers-were.txt", "jsonld": "https://wpnews.pro/news/gpt-and-claude-failed-bridgewater-s-finance-tests-because-the-right-answers-were.jsonld"}}