Surprise upset: GPT-5.5 beats Claude Fable 5 on brutal new Agents’ Last Exam benchmark - Venturebeat
Sentiment Mix
Expert Signals
Anthropic - Google News
source • 1 mention
AI-Generated Claims
Generated from linked receipts; click sources for full context.
Surprise upset: GPT-5.5 beats Claude Fable 5 on brutal new Agents' Last Exam benchmark - Venturebeat.
Supported by 2 stories
Related Events
Tell HN: Anthropic's Fable model is too expensive
LLMs • 6/11/2026
Tell HN: Anthropic's Fable model is too expensive (UND)
LLMs • 6/11/2026
DXC bets on Claude: 10x faster software, 95% of code by AI - Stock Titan
LLMs • 6/11/2026
Why Microsoft and Other Anthropic Customers Held Off On Using Claude Fable - The Information
LLMs • 6/11/2026
Claude Fable 5 will sabotage "frontier LLM research" tasks (UND)
Product Launch • 6/11/2026
Causality Chain
Preceded By
It blocked us at 'hello!' Anthropic Fable 5 refusing innocuous prompts - The Register
47 causal score
The Anthropic leader who built Claude Code says he ditched prompting — now he just writes loops. - The New Stack
47 causal score
Anthropic Recruits Fifth Third for Project Glasswing AI Cybersecurity Initiative - PYMNTS.com
45 causal score