Artificial Analysis (@ArtificialAnlys) reports Google DeepMind’s Gemini 3.8 Flash (high reasoning) scores 59 on the Intelligence Index, +3 vs Gemini 3.7 Flash and on par with GPT-5.6 Sol (xhigh) and Grok 4.6 (medium). Gains are driven by agentic evals (τ³-Banking, Terminal-Bench, GDPval). Discount pricing $0.75/$3.75 per 1M tokens through year-end puts it at ~$0.58/task on the intelligence–cost Pareto frontier.

Key Takeaways

  • ✓Intelligence Index 59 at high reasoning (+3 vs 3.7 Flash), matching GPT-5.6 Sol xhigh / Grok 4.6 medium.
  • ✓Agentic gains lead: τ³-Banking tool use, Terminal-Bench coding, and GDPval real-world tasks.
  • ✓Year-end discount $0.75/$3.75 keeps ~$0.58/task on the intelligence–cost Pareto frontier.
ADSponsored