ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemini 2.5 Pro vs Kimi K2 Instruct vs Claude Sonnet 4

Gemini 2.5 Pro comes out ahead, 77 to 66 and 55 on our weighted score, though Kimi K2 Instruct is 3.4× cheaper per token.

Price in rating: Excluded · Include price

  1. Our pick

    Google

    Gemini 2.5 Pro

    Released Jun 17, 2025

    77/100
    • ECI144.9
    • Price$1.25 / $10.00
    • Context1.05M
  2. Moonshot AI

    Kimi K2 Instruct

    Released Jul 11, 2025

    55/100
    • ECI141.3
    • Price$0.57 / $2.30
    • Context131K
  3. Anthropic

    Claude Sonnet 4

    Released May 22, 2025

    66/100
    • ECI141.9
    • Price$3.00 / $15.00
    • Context200K
01 — Verdict

Gemini 2.5 Pro is our pick

Gemini 2.5 Pro is the better all-round choice, scoring 77/100 against Claude Sonnet 4 (66) and Kimi K2 Instruct (55). It leads on capability, inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGemini 2.5 ProCapabilities Index (ECI): Gemini 2.5 Pro 144.9 · Claude Sonnet 4 141.9 · Kimi K2 Instruct 141.3
  • Lowest priceKimi K2 InstructKimi K2 Instruct $1.00 · Gemini 2.5 Pro $3.44 · Claude Sonnet 4 $6.00 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 ProGemini 2.5 Pro 1,048,576 · Claude Sonnet 4 200,000 · Kimi K2 Instruct 131,072 tokens
  • Widest inputsGemini 2.5 ProGemini 2.5 Pro: Text, Images, PDFs, Audio, Video · Kimi K2 Instruct: Text · Claude Sonnet 4: Text, Images, PDFs
  • Self-hostingKimi K2 InstructPublishes downloadable weights (Modified MIT)
How the score is built
MeasureWeightGemini 2.5 ProKimi K2 InstructClaude Sonnet 4
CapabilityCapabilities Index (ECI)67%736970
Inputs & features20%1002570
Context window13%653239
Overall100%77/10055/10066/100
02 — Side by side

Every spec in one table

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

Gemini 2.5 Pro vs Kimi K2 Instruct vs Claude Sonnet 4 specifications side by side
SpecificationGemini 2.5 ProGoogleKimi K2 InstructMoonshot AIClaude Sonnet 4Anthropic
Capability
Capabilities Index (ECI)144.9 (best)141.3141.9
ECI rank#92 of 158 (best)#108 of 158#104 of 158
GPQA DiamondGraduate-level science questions85.3% (best)—79.2%
FrontierMath Tiers 1–3Research-level mathematics24.6%——
OTIS Mock AIME 2024–2025Competition mathematics84.7% (best)—71.1%
SWE-bench VerifiedFixing real GitHub issues57.6%——
Price per million tokens
Input$1.25$0.57 (best)$3.00
Output$10.00$2.30 (best)$15.00
Cached input$0.125——
Blended (3:1)$3.44$1.00 (best)$6.00
Long-context rateOver 200K: $2.50 / $15.00Same rateSame rate
Price sourceOfficial Google APIMedian of 11 providersMedian of 10 providers
Limits
Context window1,048,576 tokens (best)131,072 tokens200,000 tokens
Max output65,536 tokens (best)32,768 tokens64,000 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoYes
AudioYesNoNo
VideoYesNoNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenModified MITProprietary
API model IDgemini-2.5-pro——
API providers31 (best)1111
ReleasedJun 17, 2025Jul 11, 2025May 22, 2025
Knowledge cutoffJan 2025—Mar 31, 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.

  • Gemini 2.5 Pro$32.50
  • Kimi K2 Instruct$10.30
  • Claude Sonnet 4$60.00
04 — Questions

Which should you choose?

Which is better: Gemini 2.5 Pro, Kimi K2 Instruct or Claude Sonnet 4?

Gemini 2.5 Pro is the better all-round choice, scoring 77/100 against Claude Sonnet 4 (66) and Kimi K2 Instruct (55). It leads on capability, inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Gemini 2.5 Pro, Kimi K2 Instruct or Claude Sonnet 4?

Kimi K2 Instruct is cheaper at $0.57 input / $2.30 output per million tokens (median across 11 API providers). Gemini 2.5 Pro costs $1.25 input / $10.00 output per million tokens (official Google API price); Claude Sonnet 4 costs $3.00 input / $15.00 output per million tokens (median across 10 API providers). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for Kimi K2 Instruct versus $3.44 for Gemini 2.5 Pro (3.4× as much) and $6.00 for Claude Sonnet 4 (6× as much).

Which scores higher on benchmarks?

Gemini 2.5 Pro scores higher on the Capabilities Index (ECI): Gemini 2.5 Pro 144.9 (#92 of 158), Claude Sonnet 4 141.9 (#104 of 158) and Kimi K2 Instruct 141.3 (#108 of 158). Their confidence ranges do not overlap (143.5–146.3 vs 140.3–143.4), so the gap is a real one.

Which is better for coding?

There are no published SWE-bench Verified results for Kimi K2 Instruct and Claude Sonnet 4 yet, so there is no like-for-like coding score. On overall capability, Gemini 2.5 Pro leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

Gemini 2.5 Pro has the largest context window at 1,048,576 tokens, against 200,000 for Claude Sonnet 4 and 131,072 for Kimi K2 Instruct. Maximum output per response: Gemini 2.5 Pro up to 65,536, Kimi K2 Instruct up to 32,768, Claude Sonnet 4 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Gemini 2.5 Pro accepts text, images, PDFs, audio and video; Kimi K2 Instruct accepts text; Claude Sonnet 4 accepts text, images and PDFs. Gemini 2.5 Pro handles the widest range of inputs.

Are any of these open source?

Kimi K2 Instruct publishes its weights (Modified MIT) and can be self-hosted; Gemini 2.5 Pro and Claude Sonnet 4 is proprietary.

Which is newer?

Kimi K2 Instruct is the newest, released Jul 11, 2025. Gemini 2.5 Pro came out Jun 17, 2025; Claude Sonnet 4 came out May 22, 2025. Knowledge cutoff: Gemini 2.5 Pro Jan 2025, Claude Sonnet 4 Mar 31, 2025.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 Nov 18, 2026.