AINewsnow

Gemini 4 Carbon takes MathArena crown from GPT-6.1 Sol at 15x the cost

Google's Gemini 4 Carbon now leads the MathArena math benchmark, ending OpenAI's GPT-6.1 Sol's run at the top, with Anthropic's Fable 5.2 also ahead; both challengers cost significantly more.

Read the full story at DEV Community — Machine Learning ↗

Timeline · 4 reports

  1. 2026-11-14 17:55 · DEV Community — Machine Learning
    Gemini 4 Carbon takes the overall MathArena crown from GPT-6.1 Sol as the first non-OpenAI leader in a while
  2. 2026-11-14 16:48 · The Decoder
    Gemini 4 Carbon takes the MathArena crown but costs 15 times more than GPT-6.1 Sol
  3. 2026-11-12 22:54 · DEV Community — AI
    I Gave Gemini 4 Carbon, Claude Fable 5.2, Opus 5.5 and GPT-6.1 Sol the Same Prompt. The AI Judges and I Disagreed.
  4. 2026-11-11 19:53 · DEV Community — Machine Learning
    Claude Fable 5.2, Gemini 4 Carbon, and Native GIF Generation in Images 2.6

More stories

  1. Anthropic launches Claude Fable 5.2, topping AI index amid rivalry with GPT-6 Astra — DEV Community — AI
  2. AWS releases AWS Emulator, a free tool that simulates 200+ services locally, saying AI agents wrote it and its team hasn't written or reviewed any of its code — Techmeme
  3. How to Export ChatGPT, Claude, and Gemini Conversations to Clean Markdown (.md) for Obsidian — DEV Community — AI
  4. ChatGPT vs Claude vs Gemini: Which AI Tool Should Professionals Actually Use? — DEV Community — AI
  5. Why Do AI Models Stream Their Responses? — DEV Community — AI
  6. I'm not a developer, and my team's AI rollout stalled. How do you see this from the building side? — DEV Community — AI
  7. How I built a 3ms self-hosted AI drift proxy in Python (and wiped deleted prompts from SQLite WAL files) — DEV Community — AI
  8. How I Built PromptBurn: A Free Tool to Count LLM Tokens and Slash API Bills ⚡🔥 — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →