ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5-Codex vs olmOCR 2 7B 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. Allenai

    olmOCR 2 7B

    Released Oct 22, 2025

    51/100
    • ECI—
    • Price$0.071 / $0.345
    • Context16K
  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 (olmOCR 2 7B 51/100, GPT-5-Codex 40/100, 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 priceolmOCR 2 7BolmOCR 2 7B $0.14 · 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 · Gemini 2.5 Computer Use Preview 128,000 · olmOCR 2 7B 16,384 tokens
  • Widest inputsSame inputsGPT-5-Codex: Text, Images · olmOCR 2 7B: Text, Images · Gemini 2.5 Computer Use Preview: Text, Images
  • Self-hostingolmOCR 2 7BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightGPT-5-CodexolmOCR 2 7BGemini 2.5 Computer Use Preview
Price50%238723
Inputs & features30%602560
Context window20%50032
Specs & price only100%40/10051/10036/100

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 olmOCR 2 7B vs Gemini 2.5 Computer Use Preview specifications side by side
SpecificationGPT-5-CodexOpenAIolmOCR 2 7BAllenaiGemini 2.5 Computer Use PreviewGoogle
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.25$0.071 (best)$1.25
Output$10.00$0.345 (best)$10.00
Cached input———
Blended (3:1)$3.44$0.14 (best)$3.44
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 9 providersMedian of 1 providersOfficial Google API
Limits
Context window400,000 tokens (best)16,384 tokens128,000 tokens
Max output128,000 tokens (best)—64,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYes
Tool callingYesNoYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenApache-2.0Proprietary
API model ID——gemini-2.5-computer-use-preview-10-2025
API providers10 (best)12
ReleasedSep 15, 2025Oct 22, 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
  • olmOCR 2 7B$1.40
  • Gemini 2.5 Computer Use Preview$32.50
04 — Questions

Which should you choose?

Which is better: GPT-5-Codex, olmOCR 2 7B or Gemini 2.5 Computer Use Preview?

There is not enough shared capability evidence to name an overall winner. The scores (olmOCR 2 7B 51/100, GPT-5-Codex 40/100, 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, olmOCR 2 7B or Gemini 2.5 Computer Use Preview?

olmOCR 2 7B is cheaper at $0.071 input / $0.345 output per million tokens (median across 1 API provider). 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 $0.14 per million tokens for olmOCR 2 7B versus $3.44 for GPT-5-Codex (25× as much) and $3.44 for Gemini 2.5 Computer Use Preview (25× 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, olmOCR 2 7B has not been scored yet 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, olmOCR 2 7B 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. Note that olmOCR 2 7B does not support tool calling, which most coding agents need.

Which has the bigger context window?

GPT-5-Codex has the largest context window at 400,000 tokens, against 128,000 for Gemini 2.5 Computer Use Preview and 16,384 for olmOCR 2 7B. Maximum output per response: GPT-5-Codex up to 128,000, 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; olmOCR 2 7B accepts text and images; Gemini 2.5 Computer Use Preview accepts text and images. They handle the same number of input types.

Are any of these open source?

olmOCR 2 7B publishes its weights (Apache-2.0) and can be self-hosted; GPT-5-Codex and Gemini 2.5 Computer Use Preview is proprietary.

Which is newer?

olmOCR 2 7B is the newest, released Oct 22, 2025. Gemini 2.5 Computer Use Preview came out Oct 7, 2025; GPT-5-Codex came out Sep 15, 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.