ZMIME
Comparison · 2 models · Updated Nov 18, 2026

olmOCR 2 7B vs Rnj-1 Instruct

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

Price in rating: Excluded · Include price

  1. Allenai

    olmOCR 2 7B

    Released Oct 22, 2025

    15/100
    • ECI—
    • Price$0.071 / $0.345
    • Context16K
  2. Essential AI

    Rnj-1 Instruct

    Released Dec 4, 2025

    19/100
    • ECI—
    • Price$0.15 / $0.15
    • Context33K
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Rnj-1 Instruct 19/100, olmOCR 2 7B 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 priceolmOCR 2 7BolmOCR 2 7B $0.14 · Rnj-1 Instruct $0.15 per 1M tokens (3:1 blend)
  • Longest contextRnj-1 InstructRnj-1 Instruct 32,768 · olmOCR 2 7B 16,384 tokens
  • Widest inputsolmOCR 2 7BolmOCR 2 7B: Text, Images · Rnj-1 Instruct: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightolmOCR 2 7BRnj-1 Instruct
Inputs & features60%2525
Context window40%011
Specs only100%15/10019/100

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.

olmOCR 2 7B vs Rnj-1 Instruct specifications side by side
SpecificationolmOCR 2 7BAllenaiRnj-1 InstructEssential AI
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input$0.071 (best)$0.15
Output$0.345$0.15 (best)
Cached input——
Blended (3:1)$0.14 (best)$0.15
Long-context rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 1 providers
Limits
Context window16,384 tokens32,768 tokens (best)
Max output—32,768 tokens
Inputs and features
TextYesYes
ImagesYesNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningNoNo
Tool callingNoYes
Structured outputNoNo
Availability
WeightsOpenApache-2.0OpenApache 2.0
API model ID——
API providers11
ReleasedOct 22, 2025Dec 4, 2025
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.

  • olmOCR 2 7B$1.40
  • Rnj-1 Instruct$1.80
04 — Questions

Which should you choose?

Which is better: olmOCR 2 7B or Rnj-1 Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Rnj-1 Instruct 19/100, olmOCR 2 7B 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, olmOCR 2 7B or Rnj-1 Instruct?

olmOCR 2 7B is cheaper at $0.071 input / $0.345 output per million tokens (median across 1 API provider). Rnj-1 Instruct costs $0.15 input / $0.15 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.14 per million tokens for olmOCR 2 7B versus $0.15 for Rnj-1 Instruct (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. olmOCR 2 7B has not been scored yet and Rnj-1 Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for olmOCR 2 7B and Rnj-1 Instruct 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?

Rnj-1 Instruct has the largest context window at 32,768 tokens, against 16,384 for olmOCR 2 7B. Maximum output per response: Rnj-1 Instruct up to 32,768 tokens.

Which can read images, PDFs, audio or video?

olmOCR 2 7B accepts text and images; Rnj-1 Instruct accepts text. olmOCR 2 7B handles the widest range of inputs.

Are any of these open source?

Yes, both publish their weights (Apache-2.0 and Apache 2.0), so you can self-host them.

Which is newer?

Rnj-1 Instruct is the newest, released Dec 4, 2025. olmOCR 2 7B came out Oct 22, 2025.

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.