ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5-Codex vs Kimi K2 Instruct vs Gemini 2.5 Computer Use Preview

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. OpenAI

    GPT-5-Codex

    Released Sep 15, 2025

    40/100
    • ECI—
    • Price$1.25 / $10.00
    • Context400K
  2. Moonshot AI

    Kimi K2 Instruct

    Released Jul 11, 2025

    38/100
    • ECI141.3
    • Price$0.57 / $2.30
    • Context131K
  3. Google

    Gemini 2.5 Computer Use Preview

    Released Oct 7, 2025

    36/100
    • ECI—
    • Price$1.25 / $10.00
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (GPT-5-Codex 40/100, Kimi K2 Instruct 38/100, Gemini 2.5 Computer Use Preview 36/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceKimi K2 InstructKimi K2 Instruct $1.00 · GPT-5-Codex $3.44 · Gemini 2.5 Computer Use Preview $3.44 per 1M tokens (3:1 blend)
  • Longest contextGPT-5-CodexGPT-5-Codex 400,000 · Kimi K2 Instruct 131,072 · Gemini 2.5 Computer Use Preview 128,000 tokens
  • Widest inputsGPT-5-Codex and Gemini 2.5 Computer Use PreviewGPT-5-Codex: Text, Images · Kimi K2 Instruct: Text · Gemini 2.5 Computer Use Preview: Text, Images
  • Self-hostingKimi K2 InstructPublishes downloadable weights (Modified MIT)
How the score is built
MeasureWeightGPT-5-CodexKimi K2 InstructGemini 2.5 Computer Use Preview
Price50%234823
Inputs & features30%602560
Context window20%503232
Specs & price only100%40/10038/10036/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

GPT-5-Codex vs Kimi K2 Instruct vs Gemini 2.5 Computer Use Preview specifications side by side
SpecificationGPT-5-CodexOpenAIKimi K2 InstructMoonshot AIGemini 2.5 Computer Use PreviewGoogle
Capability
Capabilities Index (ECI)—141.3—
ECI rank—#108 of 158—
Price per million tokens
Input$1.25$0.57 (best)$1.25
Output$10.00$2.30 (best)$10.00
Cached input———
Blended (3:1)$3.44$1.00 (best)$3.44
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 9 providersMedian of 11 providersOfficial Google API
Limits
Context window400,000 tokens (best)131,072 tokens128,000 tokens
Max output128,000 tokens (best)32,768 tokens64,000 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenModified MITProprietary
API model ID——gemini-2.5-computer-use-preview-10-2025
API providers1011 (best)2
ReleasedSep 15, 2025Jul 11, 2025Oct 7, 2025
Knowledge cutoffSep 30, 2024—Jan 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.

  • GPT-5-Codex$32.50
  • Kimi K2 Instruct$10.30
  • Gemini 2.5 Computer Use Preview$32.50
04 — Questions

Which should you choose?

Which is better: GPT-5-Codex, Kimi K2 Instruct or Gemini 2.5 Computer Use Preview?

There is not enough shared capability evidence to name an overall winner. The scores (GPT-5-Codex 40/100, Kimi K2 Instruct 38/100, Gemini 2.5 Computer Use Preview 36/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, GPT-5-Codex, Kimi K2 Instruct or Gemini 2.5 Computer Use Preview?

Kimi K2 Instruct is cheaper at $0.57 input / $2.30 output per million tokens (median across 11 API providers). GPT-5-Codex costs $1.25 input / $10.00 output per million tokens (median across 9 API providers); Gemini 2.5 Computer Use Preview costs $1.25 input / $10.00 output per million tokens (official Google 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 $3.44 for GPT-5-Codex (3.4× as much) and $3.44 for Gemini 2.5 Computer Use Preview (3.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT-5-Codex has not been scored yet, Kimi K2 Instruct has an ECI of 141.3 and Gemini 2.5 Computer Use Preview has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5-Codex, Kimi K2 Instruct and Gemini 2.5 Computer Use Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

GPT-5-Codex has the largest context window at 400,000 tokens, against 131,072 for Kimi K2 Instruct and 128,000 for Gemini 2.5 Computer Use Preview. Maximum output per response: GPT-5-Codex up to 128,000, Kimi K2 Instruct up to 32,768, Gemini 2.5 Computer Use Preview up to 64,000 tokens.

Which can read images, PDFs, audio or video?

GPT-5-Codex accepts text and images; Kimi K2 Instruct accepts text; Gemini 2.5 Computer Use Preview accepts text and images. GPT-5-Codex 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; GPT-5-Codex and Gemini 2.5 Computer Use Preview is proprietary.

Which is newer?

Gemini 2.5 Computer Use Preview is the newest, released Oct 7, 2025. GPT-5-Codex came out Sep 15, 2025; Kimi K2 Instruct came out Jul 11, 2025. Knowledge cutoff: GPT-5-Codex Sep 30, 2024, Gemini 2.5 Computer Use Preview Jan 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.