Google News SWE Bench
Claude Opus 4.7 Boosts SWE-bench to 87.6% - blockchain.news
Claude Opus 4.7 Boosts SWE-bench to 87.6% blockchain.news
Product
Claude Opus
Google News Eval Frameworks
Claude Opus 4.7, Gemini 3.1 Pro, and Others Score 0% on New SWE Benchmark - Analytics India Magazine
Claude Opus 4.7, Gemini 3.1 Pro, and Others Score 0% on New SWE Benchmark Analytics India Magazine
METR Blog
Review of the Anthropic Sabotage Risk Report: Claude Opus 4.6
External review from METR of Anthropic's Sabotage Risk Report for Claude Opus 4.6
Google News LLM Evaluation
How Anthropic’s Claude Opus 4.6 Broke Its Own AI Benchmark - WinBuzzer
How Anthropic’s Claude Opus 4.6 Broke Its Own AI Benchmark WinBuzzer