ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemini 3 Pro Preview vs Kimi K2 Instruct vs Claude Opus 4.5

Gemini 3 Pro Preview comes out ahead, 80 to 74 and 55 on our weighted score, though Kimi K2 Instruct is 4.5× cheaper per token.

Price in rating: Excluded · Include price

  1. Our pick

    Google

    Gemini 3 Pro Preview

    Released Nov 18, 2025

    80/100
    • ECI153.0
    • Price$2.00 / $12.00
    • 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 Opus 4.5

    Released Nov 24, 2025

    74/100
    • ECI151.9
    • Price$5.00 / $25.00
    • Context200K
01 — Verdict

Gemini 3 Pro Preview is our pick

Gemini 3 Pro Preview is the better all-round choice, scoring 80/100 against Claude Opus 4.5 (74) and Kimi K2 Instruct (55). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGemini 3 Pro PreviewCapabilities Index (ECI): Gemini 3 Pro Preview 153.0 · Claude Opus 4.5 151.9 · Kimi K2 Instruct 141.3
  • Lowest priceKimi K2 InstructKimi K2 Instruct $1.00 · Gemini 3 Pro Preview $4.50 · Claude Opus 4.5 $10.00 per 1M tokens (3:1 blend)
  • Longest contextGemini 3 Pro PreviewGemini 3 Pro Preview 1,048,576 · Claude Opus 4.5 200,000 · Kimi K2 Instruct 131,072 tokens
  • Widest inputsGemini 3 Pro PreviewGemini 3 Pro Preview: Text, Images, PDFs, Audio, Video · Kimi K2 Instruct: Text · Claude Opus 4.5: Text, Images, PDFs
  • Self-hostingKimi K2 InstructPublishes downloadable weights (Modified MIT)
How the score is built
MeasureWeightGemini 3 Pro PreviewKimi K2 InstructClaude Opus 4.5
CapabilityCapabilities Index (ECI)67%806979
Inputs & features20%902580
Context window13%653239
Overall100%80/10055/10074/100
02 — Side by side

Every spec in one table

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

Gemini 3 Pro Preview vs Kimi K2 Instruct vs Claude Opus 4.5 specifications side by side
SpecificationGemini 3 Pro PreviewGoogleKimi K2 InstructMoonshot AIClaude Opus 4.5Anthropic
Capability
Capabilities Index (ECI)153.0 (best)141.3151.9
ECI rank#55 of 158 (best)#108 of 158#60 of 158
GPQA DiamondGraduate-level science questions92.6% (best)—86.1%
FrontierMath Tiers 1–3Research-level mathematics——34.4%
OTIS Mock AIME 2024–2025Competition mathematics91.4% (best)—86.1%
SWE-bench VerifiedFixing real GitHub issues72.9%—76.7% (best)
SimpleQA VerifiedShort factual questions——45.7%
Price per million tokens
Input$2.00$0.57 (best)$5.00
Output$12.00$2.30 (best)$25.00
Cached input——$0.50
Blended (3:1)$4.50$1.00 (best)$10.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 6 providersMedian of 11 providersOfficial Anthropic API
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
ReasoningYesNoYeslow · medium · high
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryOpenModified MITProprietary
API model ID——claude-opus-4-5
API providers81140 (best)
ReleasedNov 18, 2025Jul 11, 2025Nov 24, 2025
Knowledge cutoffJan 2025—May 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 3 Pro Preview$44.00
  • Kimi K2 Instruct$10.30
  • Claude Opus 4.5$100.00
04 — Questions

Which should you choose?

Which is better: Gemini 3 Pro Preview, Kimi K2 Instruct or Claude Opus 4.5?

Gemini 3 Pro Preview is the better all-round choice, scoring 80/100 against Claude Opus 4.5 (74) and Kimi K2 Instruct (55). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Gemini 3 Pro Preview, Kimi K2 Instruct or Claude Opus 4.5?

Kimi K2 Instruct is cheaper at $0.57 input / $2.30 output per million tokens (median across 11 API providers). Gemini 3 Pro Preview costs $2.00 input / $12.00 output per million tokens (median across 6 API providers); Claude Opus 4.5 costs $5.00 input / $25.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for Kimi K2 Instruct versus $4.50 for Gemini 3 Pro Preview (4.5× as much) and $10.00 for Claude Opus 4.5 (10× as much).

Which scores higher on benchmarks?

Gemini 3 Pro Preview scores higher on the Capabilities Index (ECI): Gemini 3 Pro Preview 153.0 (#55 of 158), Claude Opus 4.5 151.9 (#60 of 158) and Kimi K2 Instruct 141.3 (#108 of 158). The confidence ranges of the top two overlap (151.5–154.8 vs 150.3–153.5), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for Kimi K2 Instruct yet, so there is no like-for-like coding score. On overall capability, Gemini 3 Pro Preview 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 3 Pro Preview has the largest context window at 1,048,576 tokens, against 200,000 for Claude Opus 4.5 and 131,072 for Kimi K2 Instruct. Maximum output per response: Gemini 3 Pro Preview up to 65,536, Kimi K2 Instruct up to 32,768, Claude Opus 4.5 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Gemini 3 Pro Preview accepts text, images, PDFs, audio and video; Kimi K2 Instruct accepts text; Claude Opus 4.5 accepts text, images and PDFs. Gemini 3 Pro Preview 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 3 Pro Preview and Claude Opus 4.5 is proprietary.

Which is newer?

Claude Opus 4.5 is the newest, released Nov 24, 2025. Gemini 3 Pro Preview came out Nov 18, 2025; Kimi K2 Instruct came out Jul 11, 2025. Knowledge cutoff: Gemini 3 Pro Preview Jan 2025, Claude Opus 4.5 May 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.