Google and Artificial Analysis launch MKA benchmark; Gemini 4 Carbon ranks #2 at 6x lower cost
GoogleDeepMind · x · 2026-11-11
Google DeepMind partnered with Artificial Analysis to launch MKA (Multimodal Knowledge Agent), a benchmark for how well agents handle visually complex tasks like cross-referencing blueprints and reading scientific charts — scenarios not covered by existing evaluations.
Per the shared chart, Gemini 4 Carbon ranks #2 at 54.3% (Climb WSR), just behind Claude Fable 5.2 (56.6%), ahead of Claude Opus 5.5 (53.0%) and GPT-6 Astra (50.2%) — while costing $5.63 per task, roughly 6x cheaper than the top model ($35.28). Carbon is priced at $4/$20 per 1M tokens.
Related event: DeepMind and Artificial Analysis Launch MKA Benchmark for Multimodal Agents(6 posts)→
More from Models
- xAI dumps JAX, rewrites full RL/inference stack in C/C++ as Grok 4.8 enters RL — ivan_bezdomny · 2026-11-11
- Goodfire's Curt Tigges: individual LLM neurons are far more interpretable than thought — The Cognitive Revolution · 2026-11-11
- Power User Burned 20-40B Tokens: Calls Gemini 4 Carbon His Favorite Knowledge-Work Model — rseroter · 2026-11-11
- Gemini 4 Carbon Developer Guide: When to Pick Carbon, Thinking Levels & Verify Loops — rseroter · 2026-11-11
- Gemini 4 Carbon spotted on GCI chart scoring ~134, above Gemini 4 Argon — scaling01 · 2026-11-11
- Leak: ChatGPT testing face and voice verification to confirm account changes — nima_owji · 2026-11-11