Gemini 4 Hydrogen cuts cost per intelligence task 4x vs Gemini 3.8 Flash, $7.77 to $1.87
haider1 · x · 2026-11-13
Unverified benchmark numbers for "Gemini 4 Hydrogen" show a striking efficiency jump over Gemini 3.8 Flash: cost per Artificial Analysis Intelligence Index task at high reasoning effort drops from $7.77 to $1.87 — over 4x cheaper — while xhigh reasoning lands at $3.16.
The author finds xhigh not worth it: it burns 154k output tokens per task, while high reasoning delivers a solid improvement over 3.8 Flash using 14% fewer tokens. Takeaway: high reasoning is the sweet spot for cost-efficiency.
More from Models
- Thinking Machines' Inkling 2 Small goes live on Together AI: 594B MoE, 1M context — togethercompute · 2026-11-13
- Researchers praise Kimi's new architecture for adopting attnres: "best taste" — SonglinYang4 · 2026-11-13
- Google Search rolls out Gemini 4 Hydrogen globally in its biggest model upgrade yet — koraykv · 2026-11-13
- Prominent user slams OpenAI over GPT 6.2 delays, mulls canceling ChatGPT Pro — mark_k · 2026-11-13
- Sandbox escape attempts plummet since Claude Mythos 5, but nobody knows why — peterwildeford · 2026-11-13
- New model released with 'strong' results, weights now available — clarejtbirch · 2026-11-13