ZMIME
Comparison · 3 models · Updated Nov 22, 2026

GPT-5.1 Chat vs MinerU2.5 2509 1.2B vs PaddleOCR VL

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

  1. OpenAI

    GPT-5.1 Chat

    Released Nov 13, 2025

    26/100
    • ECI—
    • Price$1.25 / $10.00
    • Context128K
  2. Opendatalab

    MinerU2.5 2509 1.2B

    Released Sep 17, 2025

    71/100
    • ECI—
    • Price$0.024 / $0.071
    • Context16K
  3. PaddlePaddle

    PaddleOCR VL

    Released Oct 16, 2025

    81/100
    • ECI—
    • Price$0.02 / $0.02
    • Context131K
  4. OpenAI

    GPT-5.1 Chat

    Released Nov 13, 2025

    32/100
    • ECI—
    • Price$1.25 / $10.00
    • Context128K
  5. Opendatalab

    MinerU2.5 2509 1.2B

    Released Sep 17, 2025

    0/100
    • ECI—
    • Price$0.024 / $0.071
    • Context16K
  6. PaddlePaddle

    PaddleOCR VL

    Released Oct 16, 2025

    32/100
    • ECI—
    • Price$0.02 / $0.02
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (PaddleOCR VL 81/100, MinerU2.5 2509 1.2B 71/100, GPT-5.1 Chat 26/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (PaddleOCR VL 32/100, GPT-5.1 Chat 32/100, MinerU2.5 2509 1.2B 0/100) compare the available specifications only. The score weighs context window 100%. 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 pricePaddleOCR VLPaddleOCR VL $0.02 · MinerU2.5 2509 1.2B $0.036 · GPT-5.1 Chat $3.44 per 1M tokens (3:1 blend)
  • Longest contextPaddleOCR VLPaddleOCR VL 131,072 · GPT-5.1 Chat 128,000 · MinerU2.5 2509 1.2B 16,384 tokens
  • Widest inputsSame inputsGPT-5.1 Chat: Text, Images · MinerU2.5 2509 1.2B: Text, Images · PaddleOCR VL: Text, Images
  • Self-hostingMinerU2.5 2509 1.2B and PaddleOCR VLPublishes downloadable weights (AGPL-3.0 and Apache-2.0)
How the score is built
MeasureWeightGPT-5.1 ChatMinerU2.5 2509 1.2BPaddleOCR VL
Price71%23100100
Context window29%32032
Specs & price only100%26/10071/10081/100

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

How the score is built
MeasureWeightGPT-5.1 ChatMinerU2.5 2509 1.2BPaddleOCR VL
Context window100%32032
Specs only100%32/1000/10032/100

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

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

GPT-5.1 Chat vs MinerU2.5 2509 1.2B vs PaddleOCR VL specifications side by side
SpecificationGPT-5.1 ChatOpenAIMinerU2.5 2509 1.2BOpendatalabPaddleOCR VLPaddlePaddle
Capability
Capabilities Index (ECI)Not publishedNot publishedNot published
ECI rankNot publishedNot publishedNot published
ECI confidence intervalNot publishedNot publishedNot published
ECI evaluation dateNot publishedNot publishedNot published
Documented capabilitiesChat-tuned GPT-5.1 for polished assistants, writing, and product conversations1.2B-parameter vision-language model from OpenDataLab for two-step document parsing: global layout analysis on downsampled images, then fine-grained text, formula, and table recognition at native resolutionCompact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
Price per million tokens
Input$1.25$0.024$0.02 (best)
Output$10.00$0.071$0.02 (best)
Cached inputNot publishedNot publishedNot published
Blended (3:1)$3.44$0.036$0.02 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 6 providersMedian of 1 providersMedian of 1 providers
Limits
Context window128,000 tokens16,384 tokens131,072 tokens (best)
Max inputNot publishedNot publishedNot published
Max output16,384 tokensNot published16,384 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoNo
Tool callingYesNoNo
Structured outputNot publishedNot publishedNot published
File attachmentsYesYesYes
Temperature controlNoYesYes
Reasoning controlalwaysNot publishedNot published
Availability
WeightsProprietaryOpenAGPL-3.0OpenApache-2.0
API model IDNot publishedNot publishedNot published
API providers6 (best)11
ReleasedNov 13, 2025Sep 17, 2025Oct 16, 2025
Knowledge cutoffSep 30, 2024Not publishedNot published
Publisher documentationNot publishedModel weightsModel weights
Source metadata updatedNov 13, 2025Sep 17, 2025Oct 16, 2025
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
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-5.1 Chat$32.50
  • MinerU2.5 2509 1.2B$0.381
  • PaddleOCR VL$0.24
04 — Questions

Which should you choose?

Which is better: GPT-5.1 Chat, MinerU2.5 2509 1.2B or PaddleOCR VL?

There is not enough shared capability evidence to name an overall winner. The scores (PaddleOCR VL 81/100, MinerU2.5 2509 1.2B 71/100, GPT-5.1 Chat 26/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (PaddleOCR VL 32/100, GPT-5.1 Chat 32/100, MinerU2.5 2509 1.2B 0/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, GPT-5.1 Chat, MinerU2.5 2509 1.2B or PaddleOCR VL?

PaddleOCR VL is cheaper at $0.02 input / $0.02 output per million tokens (median across 1 API provider). MinerU2.5 2509 1.2B costs $0.024 input / $0.071 output per million tokens (median across 1 API provider); GPT-5.1 Chat costs $1.25 input / $10.00 output per million tokens (median across 6 API providers). At a typical mix of three input tokens to one output token, that is $0.02 per million tokens for PaddleOCR VL versus $0.036 for MinerU2.5 2509 1.2B (1.8× as much) and $3.44 for GPT-5.1 Chat (172× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT-5.1 Chat has not been scored yet, MinerU2.5 2509 1.2B has not been scored yet and PaddleOCR VL has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5.1 Chat, MinerU2.5 2509 1.2B and PaddleOCR VL yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that MinerU2.5 2509 1.2B and PaddleOCR VL has no confirmed tool-calling support in this comparison.

Which has the bigger context window?

PaddleOCR VL has the largest context window at 131,072 tokens, against 128,000 for GPT-5.1 Chat and 16,384 for MinerU2.5 2509 1.2B. Maximum output per response: GPT-5.1 Chat up to 16,384, PaddleOCR VL up to 16,384 tokens.

Which can read images, PDFs, audio or video?

GPT-5.1 Chat accepts text and images; MinerU2.5 2509 1.2B accepts text and images; PaddleOCR VL accepts text and images. They handle the same number of input types.

Are any of these open source?

MinerU2.5 2509 1.2B and PaddleOCR VL publishes its weights (AGPL-3.0 and Apache-2.0) and can be self-hosted; GPT-5.1 Chat is proprietary.

Which is newer?

GPT-5.1 Chat is the newest, released Nov 13, 2025. PaddleOCR VL came out Oct 16, 2025; MinerU2.5 2509 1.2B came out Sep 17, 2025. Knowledge cutoff: GPT-5.1 Chat Sep 30, 2024.

How do you decide the winner?

This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 22, 2026.This rating uses context window (100%, 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 22, 2026.