With high reasoning, Gemini 3.8 Flash averages 48k output tokens per task, a 30% increase compared to 3.7 Flash. On low reasoning, Gemini 3.8 Flash outputs an average of 14k tokens per task, just under GP-5.6 Sol with max reasoning (17k)
Google has released Gemini 3.8 Flash, its fourth Flash model in under four months - it scores 59 on the Artificial Analysis Intelligence Index and reaches the Intelligence vs. Cost per Task Pareto frontier @GoogleDeepMind released Gemini 3.8 Flash today. With high reasoning, it- Gemini 3.8 Flash (high) costs $0.58 per Intelligence Index task, the cheapest we’ve measured at this level of intelligence. This is up ~40% from Gemini 3.7 Flash despite unchanged per-token pricing, driven by a 30% increase in output tokens per task and more turns on agentic
- On high reasoning, Gemini 3.8 Flash averages ~300 output tokens per second and a Time per Task of 2.5 minutes, just ahead of GPT-5.6 Luna (max, 2.6 minutes) and GPT-5.6 Terra (max, 3.3). Compared to Gemini 3.7 Flash, higher token usage increases Time per Task from 2.2 minutes to
- With high reasoning, Gemini 3.8 Flash averages 48k output tokens per task, a 30% increase compared to 3.7 Flash. On low reasoning, Gemini 3.8 Flash outputs an average of 14k tokens per task, just under GP-5.6 Sol with max reasoning (17k)
- On AA-Briefcase, our flagship agentic knowledge work evaluation, Gemini 3.8 Flash scores an Elo of 1213. AA-Briefcase tests models on a fully private dataset of realistic tasks across thousands of complex input files, with performance combined into a single AA-Briefcase Elo basedFull benchmark results for Gemini 3.8 Flash across high, medium and low reasoningFor further analysis, see artificialanalysis.ai/models/gemini-…
Once again Google hits the middle of the pack and nobody needs them. The more AI I use the more I replace Google. Gmail, YouTube, android. Not much left. And my AI can use Zoho programmatically but to do that with Google is a pita. & Self hosted email not that hard with agents.
