ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek OCR 2 vs Grok 4.20 (Non-Reasoning) vs MiniMax-M2 Her

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

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek OCR 2

    Released Jan 27, 2026

    15/100
    • ECI—
    • Price$0.46 / $0.749
    • Context8K
  2. xAI

    Grok 4.20 (Non-Reasoning)

    Released Mar 9, 2026

    68/100
    • ECI—
    • Price$1.25 / $2.50
    • Context1M
  3. MiniMax

    MiniMax-M2 Her

    Released Jan 23, 2026

    30/100
    • ECI—
    • Price$0.30 / $1.20
    • Context66K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Non-Reasoning) 68/100, MiniMax-M2 Her 30/100, DeepSeek OCR 2 15/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceMiniMax-M2 HerMiniMax-M2 Her $0.525 · DeepSeek OCR 2 $0.532 · Grok 4.20 (Non-Reasoning) $1.56 per 1M tokens (3:1 blend)
  • Longest contextGrok 4.20 (Non-Reasoning)Grok 4.20 (Non-Reasoning) 1,000,000 · MiniMax-M2 Her 65,536 · DeepSeek OCR 2 8,192 tokens
  • Widest inputsGrok 4.20 (Non-Reasoning)DeepSeek OCR 2: Text, Images · Grok 4.20 (Non-Reasoning): Text, Images, PDFs · MiniMax-M2 Her: Text
  • Self-hostingDeepSeek OCR 2Publishes downloadable weights
How the score is built
MeasureWeightDeepSeek OCR 2Grok 4.20 (Non-Reasoning)MiniMax-M2 Her
Inputs & features60%257035
Context window40%06422
Specs only100%15/10068/10030/100

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.

DeepSeek OCR 2 vs Grok 4.20 (Non-Reasoning) vs MiniMax-M2 Her specifications side by side
SpecificationDeepSeek OCR 2DeepSeekGrok 4.20 (Non-Reasoning)xAIMiniMax-M2 HerMiniMax
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.46$1.25$0.30 (best)
Output$0.749 (best)$2.50$1.20
Cached input—$0.20—
Blended (3:1)$0.532$1.56$0.525 (best)
Long-context rateSame rateOver 200K: $2.50 / $5.00Same rate
Price sourceMedian of 2 providersOfficial xAI APIMedian of 1 providers
Limits
Context window8,192 tokens1,000,000 tokens (best)65,536 tokens
Max output8,192 tokens30,000 tokens (best)2,048 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingNoYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryProprietary
API model ID—grok-4.20-0309-non-reasoning—
API providers313 (best)1
ReleasedJan 27, 2026Mar 9, 2026Jan 23, 2026
Knowledge cutoff———
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.

  • DeepSeek OCR 2$6.10
  • Grok 4.20 (Non-Reasoning)$17.50
  • MiniMax-M2 Her$5.40
04 — Questions

Which should you choose?

Which is better: DeepSeek OCR 2, Grok 4.20 (Non-Reasoning) or MiniMax-M2 Her?

There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Non-Reasoning) 68/100, MiniMax-M2 Her 30/100, DeepSeek OCR 2 15/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, DeepSeek OCR 2, Grok 4.20 (Non-Reasoning) or MiniMax-M2 Her?

MiniMax-M2 Her is cheaper at $0.30 input / $1.20 output per million tokens (median across 1 API provider). DeepSeek OCR 2 costs $0.46 input / $0.749 output per million tokens (median across 2 API providers); Grok 4.20 (Non-Reasoning) costs $1.25 input / $2.50 output per million tokens (official xAI API price). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M2 Her versus $0.532 for DeepSeek OCR 2 (1× as much) and $1.56 for Grok 4.20 (Non-Reasoning) (3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. DeepSeek OCR 2 has not been scored yet, Grok 4.20 (Non-Reasoning) has not been scored yet and MiniMax-M2 Her has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek OCR 2, Grok 4.20 (Non-Reasoning) and MiniMax-M2 Her yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that DeepSeek OCR 2 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) has the largest context window at 1,000,000 tokens, against 65,536 for MiniMax-M2 Her and 8,192 for DeepSeek OCR 2. Maximum output per response: DeepSeek OCR 2 up to 8,192, Grok 4.20 (Non-Reasoning) up to 30,000, MiniMax-M2 Her up to 2,048 tokens.

Which can read images, PDFs, audio or video?

DeepSeek OCR 2 accepts text and images; Grok 4.20 (Non-Reasoning) accepts text, images and PDFs; MiniMax-M2 Her accepts text. Grok 4.20 (Non-Reasoning) handles the widest range of inputs.

Are any of these open source?

DeepSeek OCR 2 publishes its weights and can be self-hosted; Grok 4.20 (Non-Reasoning) and MiniMax-M2 Her is proprietary.

Which is newer?

Grok 4.20 (Non-Reasoning) is the newest, released Mar 9, 2026. DeepSeek OCR 2 came out Jan 27, 2026; MiniMax-M2 Her came out Jan 23, 2026.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.