Compare / Gemini 3.1 Flash-Lite Preview vs Gemini 3.5 Flash-Lite

Gemini 3.1 Flash-Lite Preview vs Gemini 3.5 Flash-Lite

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 2 sources that measured both models.

GoogleGemini 3.1 Flash-Lite Preview Released 3 Mar 2026 · $0.25 in · $1.50 out
GoogleGemini 3.5 Flash-Lite Released 21 Jul 2026 · $0.30 in · $2.50 out
Gemini 3.1 Flash-Lite Preview wins 1Gemini 3.5 Flash-Lite wins 15

Of the 16 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

Gemini 3.1 Flash-Lite Preview or Gemini 3.5 Flash-Lite? The short answer

Gemini 3.5 Flash-Lite is the newer version and scores higher (Intelligence Index 22.2 against 15.6), but Gemini 3.1 Flash-Lite Preview is cheaper (34% less per token): upgrade if the gain is worth the price.

  • Gemini 3.1 Flash-Lite Preview is cheaper: $0.56 against $0.85 per million tokens, 34% less.
  • Gemini 3.5 Flash-Lite scores higher on the Artificial Analysis Intelligence Index: 22.2 against 15.6.
  • Gemini 3.5 Flash-Lite is newer: released 21 Jul 2026, against 3 Mar 2026 for Gemini 3.1 Flash-Lite Preview.
  • On third-party benchmarks, on the results both models have: Gemini 3.5 Flash-Lite does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

15.6
Intelligence Index
22.2
$0.56
Price per million tokens, blendedlower is better
$0.85
1,048,576
Context window, tokens
1,048,576

Every fact side by side

Gemini 3.1 Flash-Lite PreviewGemini 3.5 Flash-Lite
Price per million tokens$0.25 in · $1.50 out$0.30 in · $2.50 out
Blended (3 in : 1 out)$0.56$0.85
Cheapest host, blended–$0.85 (Google)
Cached input, per million–$0.030 cached input
Intelligence Index15.622.2
Spring Prompt overall–24
Output speed, tokens a second–398
Context window1,048,576 tokens1,048,576 tokens
Released3 Mar 202621 Jul 2026 (newer)
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 not measured 28 of 35
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 32 of 35
User surveysPlanning a user survey and reading its results without being misled not measured 21 of 26
Marketing planningPlanning a year of ad spend without overspending not measured 31 of 35
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 107 of 159 81 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 46 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 109 of 187 98 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 80 of 169 49 of 169
Sticking to the factsSummarising without inventing things, and factual answers 72 of 139 61 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 2 of 38

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 3.1 Flash-Lite PreviewGemini 3.5 Flash-Lite
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 94 · 61 of 387 measured 1,433 1,455
Overall · Text factualityArena rating, higher is better 93 · 63 of 163 measured 1,433 1,447
Business, management and finance · TextArena rating, higher is better 107 · 63 of 380 measured 1,420 1,452
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 129 · 97 of 249 measured 15.6 22.2
GPQA Diamond% of questions, higher is better 101 · 91 of 232 measured 82.2% 83.8%
Humanity's Last Exam% of questions, higher is better 125 · 122 of 250 measured 17.2% 18.8%
Show all 16 results (10 more)
MeasureGemini 3.1 Flash-Lite PreviewGemini 3.5 Flash-Lite
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 76 · 52 of 385 measured 1,413 1,436
Expert prompts · TextArena rating, higher is better 108 · 78 of 338 measured 1,443 1,470
Instruction following · TextArena rating, higher is better 112 · 67 of 387 measured 1,407 1,443
Writing, literature and language · TextArena rating, higher is better 81 · 56 of 386 measured 1,420 1,443
Artificial Analysis reported by Artificial Analysis · 6 results
Terminal-Bench 2.1% of tasks, higher is better 81 · 58 of 131 measured 31.1% 53.6%
Terminal-Bench 4.0% of tasks, higher is better 65 · 59 of 120 measured 0.5% 1.0%
τ-bench banking% of tasks, higher is better 79 · 52 of 121 measured 9.7% 17.5%
Artificial Analysis Coding Indexindex score, higher is better 80 · 58 of 130 measured 34.7 49.3
Long-context reasoning (AA-LCR)% of questions, higher is better 89 · 80 of 241 measured 74.3% 76.0%
SciCode% of problems, higher is better 78 · 83 of 121 measured 43.4% 41.3%

Quick answers

Is Gemini 3.1 Flash-Lite Preview better than Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite is the newer version and scores higher (Intelligence Index 22.2 against 15.6), but Gemini 3.1 Flash-Lite Preview is cheaper (34% less per token): upgrade if the gain is worth the price.

Which is cheaper, Gemini 3.1 Flash-Lite Preview or Gemini 3.5 Flash-Lite?

Gemini 3.1 Flash-Lite Preview is cheaper: $0.56 against $0.85 per million tokens, 34% less.

Which is better for agents and tool use, Gemini 3.1 Flash-Lite Preview or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite ranks 81 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 107 for Gemini 3.1 Flash-Lite Preview.

Which is better for reasoning and knowledge, Gemini 3.1 Flash-Lite Preview or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite ranks 98 of 187 models on sale for hard questions across science, maths and general knowledge, against 109 for Gemini 3.1 Flash-Lite Preview.

Which is better for writing, Gemini 3.1 Flash-Lite Preview or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite ranks 49 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 80 for Gemini 3.1 Flash-Lite Preview.

Which is better for sticking to the facts, Gemini 3.1 Flash-Lite Preview or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite ranks 61 of 139 models on sale for summarising without inventing things, and factual answers, against 72 for Gemini 3.1 Flash-Lite Preview.

Run Gemini 3.1 Flash-Lite Preview and Gemini 3.5 Flash-Lite 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.