Compare / Gemini 3.8 Flash vs Gemini 3 Flash Preview

Gemini 3.8 Flash vs Gemini 3 Flash Preview

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 6 sources that measured both models.

GoogleGemini 3.8 Flash Released 2 Sep 2026 · $1.50 in · $7.50 out
GoogleGemini 3 Flash Preview Released 17 Dec 2025 · $0.50 in · $3.00 out
Gemini 3.8 Flash wins 161 too close to callGemini 3 Flash Preview wins 1

Of the 18 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

Gemini 3.8 Flash or Gemini 3 Flash Preview? The short answer

Pick Gemini 3.8 Flash if quality matters most: it scores higher (Intelligence Index 40.9 against 26.3). Pick Gemini 3 Flash Preview if cost matters more: it costs 2.7 times less per token.

  • Gemini 3 Flash Preview is cheaper: $1.12 against $3.00 per million tokens, 2.7 times less.
  • Gemini 3.8 Flash scores higher on the Artificial Analysis Intelligence Index: 40.9 against 26.3.
  • Gemini 3.8 Flash is newer: released 2 Sep 2026, against 17 Dec 2025 for Gemini 3 Flash Preview.
  • On third-party benchmarks, on the results both models have: Gemini 3.8 Flash does better for agents and tool use, professional work, reasoning and knowledge, writing and sticking to the facts.

Head to head

40.9
Intelligence Index
26.3
$3.00
Price per million tokens, blendedlower is better
$1.12
1,048,576
Context window, tokens
1,048,576

Every fact side by side

Gemini 3.8 FlashGemini 3 Flash Preview
Price per million tokens$1.50 in · $7.50 out$0.50 in · $3.00 out
Blended (3 in : 1 out)$3.00$1.12
Cheapest host, blended$1.50 (Google)$1.12 (Google)
Intelligence Index40.926.3
Spring Prompt overall58–
Output speed, tokens a second141–
Context window1,048,576 tokens1,048,576 tokens
Released2 Sep 2026 (newer)17 Dec 2025
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 22 of 32 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 26 of 32 not measured
User surveysPlanning a user survey and reading its results without being misled 16 of 23 not measured
Marketing planningPlanning a year of ad spend without overspending 11 of 32 not measured
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 35 of 159 85 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 11 of 51 46 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 15 of 187 60 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 3 of 169 28 of 169
Sticking to the factsSummarising without inventing things, and factual answers 12 of 139 53 of 139
Speed under pressureGood decisions against a real clock (fast chess) 13 of 35 not measured

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureGemini 3.8 FlashGemini 3 Flash Preview
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 7 · 36 of 387 measured 1,495high reasoning 1,473
Overall · Text factualityArena rating, higher is better 16 · 27 of 163 measured 1,477high reasoning 1,468
Business, management and finance · TextArena rating, higher is better 21 · 34 of 380 measured 1,481high reasoning 1,468
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 25 · 71 of 249 measured 40.9high reasoning 26.3thinking reasoning
GPQA Diamond% of questions, higher is better 2 · 44 of 232 measured 95.3%high reasoning 89.8%thinking reasoning
Humanity's Last Exam% of questions, higher is better 18 · 60 of 250 measured 47.8%high reasoning 36.6%thinking reasoning
GDP.pdf reported by GDP.pdf · 1 result
Professional document tasks% of rubric, higher is better 12 · 29 of 32 measured 23.4%medium reasoning 10.0%
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 7 · 10 of 76 measured 69.7%high reasoning 66.8%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 1 · 18 of 230 measured 78.6medium reasoning 67.7medium reasoning
Requested-length error · UGI% off the requested word count, lower is better 57 · 76 of 230 measured 13.0%high reasoning 16.0%minimal reasoning
Style adherence · UGIscore from 0 to 1, higher is better 132 · 52 of 230 measured 0.34high reasoning 0.37high reasoning
Vending-Bench 2 reported by Vending-Bench 2 · 1 result
Money after a yearUS dollars, higher is better 26 · 36 of 58 measured $5,094 $3,635
Show all 18 results (6 more)
MeasureGemini 3.8 FlashGemini 3 Flash Preview
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 7 · 23 of 385 measured 1,485high reasoning 1,457
Expert prompts · TextArena rating, higher is better 13 · 44 of 338 measured 1,526high reasoning 1,496
Instruction following · TextArena rating, higher is better 12 · 44 of 387 measured 1,486high reasoning 1,457
Writing, literature and language · TextArena rating, higher is better 8 · 28 of 386 measured 1,487high reasoning 1,461
Artificial Analysis reported by Artificial Analysis · 2 results
τ-bench banking% of tasks, higher is better 11 · 48 of 121 measured 45.8%medium reasoning 20.8%thinking reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 7 · 65 of 241 measured 84.0%medium reasoning 78.0%thinking reasoning

Quick answers

Is Gemini 3.8 Flash better than Gemini 3 Flash Preview?

Pick Gemini 3.8 Flash if quality matters most: it scores higher (Intelligence Index 40.9 against 26.3). Pick Gemini 3 Flash Preview if cost matters more: it costs 2.7 times less per token.

Which is cheaper, Gemini 3.8 Flash or Gemini 3 Flash Preview?

Gemini 3 Flash Preview is cheaper: $1.12 against $3.00 per million tokens, 2.7 times less.

Which is better for agents and tool use, Gemini 3.8 Flash or Gemini 3 Flash Preview?

Gemini 3.8 Flash ranks 35 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 85 for Gemini 3 Flash Preview.

Which is better for professional work, Gemini 3.8 Flash or Gemini 3 Flash Preview?

Gemini 3.8 Flash ranks 11 of 51 models on sale for real tasks from banking, consulting and law, business documents and freelance projects, against 46 for Gemini 3 Flash Preview.

Which is better for reasoning and knowledge, Gemini 3.8 Flash or Gemini 3 Flash Preview?

Gemini 3.8 Flash ranks 15 of 187 models on sale for hard questions across science, maths and general knowledge, against 60 for Gemini 3 Flash Preview.

Which is better for writing, Gemini 3.8 Flash or Gemini 3 Flash Preview?

Gemini 3.8 Flash ranks 3 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 28 for Gemini 3 Flash Preview.

Which is better for sticking to the facts, Gemini 3.8 Flash or Gemini 3 Flash Preview?

Gemini 3.8 Flash ranks 12 of 139 models on sale for summarising without inventing things, and factual answers, against 53 for Gemini 3 Flash Preview.

Run Gemini 3.8 Flash and Gemini 3 Flash Preview on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.