Skip to content
ModelCap

Head-to-head comparison

Gemini 3.1 Pro Preview vs Gemini 3.5 Flash Lite

Gemini 3.1 Pro Preview (Google) and Gemini 3.5 Flash Lite (Google) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 22 September 2026

As of 22 September 2026, Gemini 3.1 Pro Preview holds the stronger ModelCap Index position (#17 vs #33); and Gemini 3.5 Flash Lite is 4.8× cheaper per output token ($2.50/1M vs $12.00/1M).

Which should you choose?

Choose Gemini 3.1 Pro Preview if…

  • you want the stronger overall ModelCap Index position — #17 against #33 (81.5 vs 72.2 points).
  • Arena coding is your yardstick — 1520 against 1504.
  • LMArena Agent is your yardstick — -5.8% against -15.3%.
  • AA Intelligence Index is your yardstick — 29.7 against 22.2.
  • AA Humanity's Last Exam is your yardstick — 47.0% against 18.8%.

Choose Gemini 3.5 Flash Lite if…

  • API cost matters — $2.50/1M output tokens against $12.00/1M, about 4.8× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.30/1M against $2.00/1M.
  • you want the more recently listed model — Gemini 3.5 Flash Lite was listed 21 July 2026, Gemini 3.1 Pro Preview 19 February 2026.

Gemini 3.1 Pro Preview vs Gemini 3.5 Flash Lite: specs, pricing and context

Specification comparison of Gemini 3.1 Pro Preview and Gemini 3.5 Flash Lite
FieldGemini 3.1 Pro PreviewGoogleGemini 3.5 Flash LiteGoogle
ModelCap Index position#17#33
Index score81.572.2
EvidenceMeasuredMeasured
Input price / 1M tokens$2.00$0.30
Output price / 1M tokens$12.00$2.50
Context window1M tokens1M tokens
Max output tokens66K66K
API providers listed22
Weight accessAPI onlyAPI only
Input modalitiesAudio, File, Image, Text, VideoText, Image, Video, File, Audio
First listed19 February 202621 July 2026
PublisherGoogleGoogle

Evidence: 4 public benchmark observations across 4 boards · 5 public benchmark observations across 5 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Gemini 3.1 Pro Preview vs Gemini 3.5 Flash Lite

Public benchmark boards where Gemini 3.1 Pro Preview or Gemini 3.5 Flash Lite has a published result
BoardGemini 3.1 Pro PreviewGemini 3.5 Flash LiteLeads
Arena codingArena (LMArena)15201515–152515041496–1512Gemini 3.1 Pro Preview
LMArena AgentLMArena-5.8%-6.6%–-5.0%-15.3%-16.7%–-14.0%Gemini 3.1 Pro Preview
ARC-AGI-2ARC Prize Foundation—10.3%HighOnly one result
AA Intelligence IndexArtificial Analysis29.7intelligence-index:v4.3:reasoning-unspecified22.2intelligence-index:v4.3:reasoning-unspecifiedGemini 3.1 Pro Preview
AA τ²-Bench TelecomArtificial Analysis95.6%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Gemini 3.1 Pro Preview":reasoning=true—Only one result
AA Humanity's Last ExamArtificial Analysis47.0%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Gemini 3.1 Pro Preview":reasoning=true18.8%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Gemini 3.5 Flash-Lite":reasoning=trueGemini 3.1 Pro Preview

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Gemini 3.1 Pro Preview vs Gemini 3.5 Flash Lite: common questions

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

Gemini 3.1 Pro Preview ranks higher on the ModelCap Index as of 22 September 2026: #17 against #33. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is Gemini 3.1 Pro Preview cheaper than Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite is cheaper on output tokens: $2.50/1M against $12.00/1M. Input tokens are $2.00/1M for Gemini 3.1 Pro Preview and $0.30/1M for Gemini 3.5 Flash Lite. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $10.00 for Gemini 3.1 Pro Preview versus $1.85 for Gemini 3.5 Flash Lite. Gemini 3.5 Flash Lite costs 81.5% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, Gemini 3.1 Pro Preview or Gemini 3.5 Flash Lite?

Both publish a 1M-token context window.

Which is better for coding, Gemini 3.1 Pro Preview or Gemini 3.5 Flash Lite?

Arena coding: Gemini 3.1 Pro Preview 1520, Gemini 3.5 Flash Lite 1504 — Gemini 3.1 Pro Preview leads.

Are Gemini 3.1 Pro Preview and Gemini 3.5 Flash Lite open-weight models?

Gemini 3.1 Pro Preview: API only. Gemini 3.5 Flash Lite: API only. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Gemini 3.1 Pro Preview and Gemini 3.5 Flash Lite?

ModelCap currently lists 2 API providers for Gemini 3.1 Pro Preview and 2 for Gemini 3.5 Flash Lite, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Gemini 3.1 Pro Preview vs Gemini 3.5 Flash Lite comparison?

Every figure comes from the sealed ModelCap dataset published 22 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further