Gemini 4 Carbon takes #1 on Vending-Bench 2 at lower cost than rivals
vedantmisra · x · 2026-10-31
Google's Gemini 4 Carbon is #1 on Andon Labs' Vending-Bench 2 for the first time in a year, ending OpenAI's streak — and per the score-vs-cost chart it runs notably cheaper than same-tier frontier models. The benchmark tests long-horizon agentic decision-making.
More from Models
- Anthropic's Claude Code now steers away from cloning games; devs push back — sytelus · 2026-10-31
- Gemini Argon quota test: $99 Ultra plan drained to 16% after 3 days of heavy use — teortaxesTex · 2026-10-31
- Inside Decision Models: How Perplexity's Decider Works and When to Use One — antoine_chaffin · 2026-10-31
- GPT-6.5 Astra rumored to be a beast, hinting at OpenAI's next model — daniel_mac8 · 2026-10-31
- Anthropic's poisoned-dataset alignment test sparks speculation about distillation sabotage — teortaxesTex · 2026-10-31
- Particle-1, a token-efficient model, launches on Cloudflare AI Gateway — garrytan · 2026-10-31