MKA cost breakdown: Claude Fable 5.2 spends $68 and 3 hours on a task Gemini 4 Carbon does for $8
ArtificialAnlys · x · 2026-11-11
Artificial Analysis shared a same-task cost comparison from MKA: Claude Fable 5.2 (max) used 224 turns, 3 hours and $68 to produce a building-audit deck scoring 87%, while Gemini 4 Carbon (high) finished in 76 turns, 1 hour and $8 at 72%. Carbon viewed images 118 times vs Fable's 203.
By deliverable type, Fable 5.2 leads PDF, Word, narrowly Spreadsheet and Presentation; Gemini 4 Argon/Carbon lead Image, and DeepSeek V4.1 Flash 1017 leads Text Files. Word and text outputs are hardest — no model exceeds 52%.
Related event: MKA cost test: Gemini Carbon finishes at $8 vs Claude Fable's $68(2 posts)→
More from Models
- TheZmi flags Fable 5.2 regression: actively less robust across model card benchmarks — TheZvi · 2026-11-11
- Siri AI's Skimmer: regex-only fast path calls tools up to 20× faster than LLMs — SumitGup · 2026-11-11
- Stripe CEO: Higher Reasoning Effort Thinks Harder Per Option, Not About More Options — gabriel1 · 2026-11-11
- Poll: 70% say Anthropic's best internal model plus $50M can dominate any human expert — JacquesThibs · 2026-11-11
- Ollama cloud 'DeepSeek' claimed it was actually ChatGPT, user alleges model swapping — No_Literature_7653 · 2026-11-11
- Rumor: Anthropic's Claude 4 said to be 'very different' in cyber and RSI capabilities — ChrisGPT · 2026-11-11