Skip to content
ModelCap

Head-to-head comparison

Claude Sonnet 5 vs Gemini 3.1 Pro Preview

Claude Sonnet 5 (Anthropic) and Gemini 3.1 Pro Preview (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 #26); and Claude Sonnet 5 is 1.2× cheaper per output token ($10.00/1M vs $12.00/1M).

Which should you choose?

Choose Claude Sonnet 5 if…

  • API cost matters — $10.00/1M output tokens against $12.00/1M, about 1.2× cheaper.
  • you want provider choice — 5 listed API providers against 2.
  • Arena coding is your yardstick — 1520 against 1520.
  • LMArena Agent is your yardstick — 6.0% against -5.8%.
  • AA Intelligence Index is your yardstick — 38.2 against 29.7.
  • you want the more recently listed model — Claude Sonnet 5 was listed 30 June 2026, Gemini 3.1 Pro Preview 19 February 2026.

Choose Gemini 3.1 Pro Preview if…

  • you want the stronger overall ModelCap Index position — #17 against #26 (81.5 vs 78.5 points).
  • AA Humanity's Last Exam is your yardstick — 47.0% against 41.3%.

Claude Sonnet 5 vs Gemini 3.1 Pro Preview: specs, pricing and context

Specification comparison of Claude Sonnet 5 and Gemini 3.1 Pro Preview
FieldClaude Sonnet 5AnthropicGemini 3.1 Pro PreviewGoogle
ModelCap Index position#26#17
Index score78.581.5
EvidenceMeasuredMeasured
Input price / 1M tokens$2.00$2.00
Output price / 1M tokens$10.00$12.00
Context window1M tokens1M tokens
Max output tokens128K66K
API providers listed52
Weight accessAPI onlyAPI only
Input modalitiesText, Image, FileAudio, File, Image, Text, Video
First listed30 June 202619 February 2026
PublisherAnthropicGoogle

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

Benchmark scores: Claude Sonnet 5 vs Gemini 3.1 Pro Preview

Public benchmark boards where Claude Sonnet 5 or Gemini 3.1 Pro Preview has a published result
BoardClaude Sonnet 5Gemini 3.1 Pro PreviewLeads
Arena codingArena (LMArena)15201513–1527High15201515–1525Claude Sonnet 5
LMArena AgentLMArena6.0%4.4%–7.6%High-5.8%-6.6%–-5.0%Claude Sonnet 5
AA Intelligence IndexArtificial Analysis38.2intelligence-index:v4.3:max29.7intelligence-index:v4.3:reasoning-unspecifiedClaude Sonnet 5
AA τ²-Bench TelecomArtificial Analysis—95.6%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Gemini 3.1 Pro Preview":reasoning=trueOnly one result
AA Humanity's Last ExamArtificial Analysis41.3%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Claude Sonnet 5 (Adaptive Reasoning, Max Effort)":reasoning=true47.0%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Gemini 3.1 Pro Preview":reasoning=trueGemini 3.1 Pro Preview
Terminal-Bench 4.0Terminal-Bench (Laude Institute)12.4%9.4%–15.5%Claude Code · Max—Only one result

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.

Claude Sonnet 5 vs Gemini 3.1 Pro Preview: common questions

Is Claude Sonnet 5 better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview ranks higher on the ModelCap Index as of 22 September 2026: #17 against #26. 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 Claude Sonnet 5 cheaper than Gemini 3.1 Pro Preview?

Claude Sonnet 5 is cheaper on output tokens: $10.00/1M against $12.00/1M. Input tokens are $2.00/1M for Claude Sonnet 5 and $2.00/1M for Gemini 3.1 Pro Preview. 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 $9.00 for Claude Sonnet 5 versus $10.00 for Gemini 3.1 Pro Preview. Claude Sonnet 5 costs 10.0% 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, Claude Sonnet 5 or Gemini 3.1 Pro Preview?

Both publish a 1M-token context window.

Which is better for coding, Claude Sonnet 5 or Gemini 3.1 Pro Preview?

Arena coding: Claude Sonnet 5 1520, Gemini 3.1 Pro Preview 1520 — Claude Sonnet 5 leads.

Are Claude Sonnet 5 and Gemini 3.1 Pro Preview open-weight models?

Claude Sonnet 5: API only. Gemini 3.1 Pro Preview: 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 Claude Sonnet 5 and Gemini 3.1 Pro Preview?

ModelCap currently lists 5 API providers for Claude Sonnet 5 and 2 for Gemini 3.1 Pro Preview, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Claude Sonnet 5 vs Gemini 3.1 Pro Preview 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