ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Claude Sonnet 5 vs Gemini 3 Pro Preview

Too close to call on our weighted score (Gemini 3 Pro Preview 67, Claude Sonnet 5 66). The right pick depends on what you value most.

  1. Anthropic

    Claude Sonnet 5

    Released Jun 30, 2026

    66/100
    • ECI156.3
    • Price$2.00 / $10.00
    • Context1M
    Full specs Remove Claude Sonnet 5

  2. Google

    Gemini 3 Pro Preview

    Released Nov 18, 2025

    67/100
    • ECI153.0
    • Price$2.00 / $12.00
    • Context1.05M
    Full specs Remove Gemini 3 Pro Preview

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Too close to call

It is close. Our weighted score puts them within a point (Gemini 3 Pro Preview 67/100, Claude Sonnet 5 66/100), so choose by what matters most for your work: Claude Sonnet 5 for raw capability and Gemini 3 Pro Preview for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityClaude Sonnet 5Capabilities Index (ECI): Claude Sonnet 5 156.3 · Gemini 3 Pro Preview 153.0
  • Lowest priceClaude Sonnet 5Claude Sonnet 5 $4.00 · Gemini 3 Pro Preview $4.50 per 1M tokens (3:1 blend)
  • Longest contextGemini 3 Pro PreviewGemini 3 Pro Preview 1,048,576 · Claude Sonnet 5 1,000,000 tokens
  • Widest inputsGemini 3 Pro PreviewClaude Sonnet 5: Text, Images, PDFs · Gemini 3 Pro Preview: Text, Images, PDFs, Audio, Video
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightClaude Sonnet 5Gemini 3 Pro Preview
CapabilityCapabilities Index (ECI)50%8682
Price25%2119
Inputs & features15%80100
Context window10%6061
Overall100%66/10067/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Claude Sonnet 5 vs Gemini 3 Pro Preview specifications side by side
SpecificationClaude Sonnet 5AnthropicGemini 3 Pro PreviewGoogle
Capability
Capabilities Index (ECI)156.3 (best)153.0
ECI rank#23 of 148 (best)#39 of 148
GPQA DiamondGraduate-level science questions90.5%92.6% (best)
FrontierMath Tiers 1–3Research-level mathematics65.6%—
OTIS Mock AIME 2024–2025Competition mathematics94.7% (best)91.4%
SWE-bench VerifiedFixing real GitHub issues—72.9%
SimpleQA VerifiedShort factual questions33.7%—
Price per million tokens
Input$2.00$2.00
Output$10.00 (best)$12.00
Cached input$0.20—
Blended (3:1)$4.00 (best)$4.50
Long-context rateSame rateSame rate
Price sourceOfficial Anthropic APIMedian of 2 providers
Limits
Context window1,000,000 tokens1,048,576 tokens (best)
Max output128,000 tokens (best)65,536 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesYes
AudioNoYes
VideoNoYes
ReasoningYeslow · medium · high · xhigh · maxYes
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDclaude-sonnet-5—
API providers38 (best)3
ReleasedJun 30, 2026Nov 18, 2025
Knowledge cutoffJan 31, 2026Jan 2025
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Claude Sonnet 5$40.00
  • Gemini 3 Pro Preview$44.00
04 — Questions

Which should you choose?

Which is better: Claude Sonnet 5 or Gemini 3 Pro Preview?

It is close. Our weighted score puts them within a point (Gemini 3 Pro Preview 67/100, Claude Sonnet 5 66/100), so choose by what matters most for your work: Claude Sonnet 5 for raw capability and Gemini 3 Pro Preview for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Sonnet 5 or Gemini 3 Pro Preview?

Claude Sonnet 5 is cheaper at $2.00 input / $10.00 output per million tokens (official Anthropic API price). Gemini 3 Pro Preview costs $2.00 input / $12.00 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $4.00 per million tokens for Claude Sonnet 5 versus $4.50 for Gemini 3 Pro Preview (1.1× as much).

Which scores higher on benchmarks?

Claude Sonnet 5 scores higher on the Capabilities Index (ECI): Claude Sonnet 5 156.3 (#23 of 148) and Gemini 3 Pro Preview 153.0 (#39 of 148). The confidence ranges of the top two overlap (153.6–158.8 vs 150.6–155.2), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3 Pro Preview 92.6%, Claude Sonnet 5 90.5%; OTIS Mock AIME 2024–2025 — Claude Sonnet 5 94.7%, Gemini 3 Pro Preview 91.4%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Sonnet 5 yet, so there is no like-for-like coding score. On overall capability, Claude Sonnet 5 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

Gemini 3 Pro Preview has the largest context window at 1,048,576 tokens, against 1,000,000 for Claude Sonnet 5. Maximum output per response: Claude Sonnet 5 up to 128,000, Gemini 3 Pro Preview up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Claude Sonnet 5 accepts text, images and PDFs; Gemini 3 Pro Preview accepts text, images, PDFs, audio and video. Gemini 3 Pro Preview handles the widest range of inputs.

Are any of these open source?

No. Claude Sonnet 5 and Gemini 3 Pro Preview are proprietary and only available through APIs and apps.

Which is newer?

Claude Sonnet 5 is the newest, released Jun 30, 2026. Gemini 3 Pro Preview came out Nov 18, 2025. Knowledge cutoff: Claude Sonnet 5 Jan 31, 2026, Gemini 3 Pro Preview Jan 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons