ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aion-RP 1.0 (8B) vs GPT-4o vs Qwen2.5-VL 72B 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. Aion Labs

    Aion-RP 1.0 (8B)

    Released Feb 4, 2025

    4/100
    • ECI—
    • Price$0.80 / $1.60
    • Context33K
  2. OpenAI

    GPT-4o

    Released May 13, 2024

    55/100
    • ECI128.1
    • Price$2.50 / $10.00
    • Context128K
  3. Alibaba (Qwen)

    Qwen2.5-VL 72B Instruct

    Released Jan 26, 2025

    43/100
    • ECI—
    • Price$1.01 / $1.01
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (GPT-4o 55/100, Qwen2.5-VL 72B Instruct 43/100, Aion-RP 1.0 (8B) 4/100) 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 priceAion-RP 1.0 (8B)Aion-RP 1.0 (8B) $1.00 · Qwen2.5-VL 72B Instruct $1.01 · GPT-4o $4.38 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5-VL 72B InstructQwen2.5-VL 72B Instruct 131,072 · GPT-4o 128,000 · Aion-RP 1.0 (8B) 32,768 tokens
  • Widest inputsGPT-4oAion-RP 1.0 (8B): Text · GPT-4o: Text, Images, PDFs · Qwen2.5-VL 72B Instruct: Text, Images
  • Self-hostingAion-RP 1.0 (8B) and Qwen2.5-VL 72B InstructPublishes downloadable weights
How the score is built
MeasureWeightAion-RP 1.0 (8B)GPT-4oQwen2.5-VL 72B Instruct
Inputs & features60%07050
Context window40%113232
Specs only100%4/10055/10043/100

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.

Aion-RP 1.0 (8B) vs GPT-4o vs Qwen2.5-VL 72B Instruct specifications side by side
SpecificationAion-RP 1.0 (8B)Aion LabsGPT-4oOpenAIQwen2.5-VL 72B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)—128.1—
ECI rank—#139 of 158—
GPQA DiamondGraduate-level science questions—48.9%—
OTIS Mock AIME 2024–2025Competition mathematics—6.3%—
Price per million tokens
Input$0.80 (best)$2.50$1.01
Output$1.60$10.00$1.01 (best)
Cached input—$1.25—
Blended (3:1)$1.00 (best)$4.38$1.01
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 4 providersOfficial OpenAI APIMedian of 5 providers
Limits
Context window32,768 tokens128,000 tokens131,072 tokens (best)
Max output29,491 tokens (best)16,384 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingNoYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryOpen
API model ID—gpt-4o—
API providers427 (best)5
ReleasedFeb 4, 2025May 13, 2024Jan 26, 2025
Knowledge cutoffDec 31, 2023Sep 2023Apr 2024
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.

  • Aion-RP 1.0 (8B)$11.20
  • GPT-4o$45.00
  • Qwen2.5-VL 72B Instruct$12.12
04 — Questions

Which should you choose?

Which is better: Aion-RP 1.0 (8B), GPT-4o or Qwen2.5-VL 72B Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (GPT-4o 55/100, Qwen2.5-VL 72B Instruct 43/100, Aion-RP 1.0 (8B) 4/100) 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, Aion-RP 1.0 (8B), GPT-4o or Qwen2.5-VL 72B Instruct?

Aion-RP 1.0 (8B) is cheaper at $0.80 input / $1.60 output per million tokens (median across 4 API providers). Qwen2.5-VL 72B Instruct costs $1.01 input / $1.01 output per million tokens (median across 5 API providers); GPT-4o costs $2.50 input / $10.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for Aion-RP 1.0 (8B) versus $1.01 for Qwen2.5-VL 72B Instruct (1× as much) and $4.38 for GPT-4o (4.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Aion-RP 1.0 (8B) has not been scored yet, GPT-4o has an ECI of 128.1 and Qwen2.5-VL 72B Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Aion-RP 1.0 (8B), GPT-4o and Qwen2.5-VL 72B Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aion-RP 1.0 (8B) does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen2.5-VL 72B Instruct has the largest context window at 131,072 tokens, against 128,000 for GPT-4o and 32,768 for Aion-RP 1.0 (8B). Maximum output per response: Aion-RP 1.0 (8B) up to 29,491, GPT-4o up to 16,384, Qwen2.5-VL 72B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Aion-RP 1.0 (8B) accepts text; GPT-4o accepts text, images and PDFs; Qwen2.5-VL 72B Instruct accepts text and images. GPT-4o handles the widest range of inputs.

Are any of these open source?

Aion-RP 1.0 (8B) and Qwen2.5-VL 72B Instruct publishes its weights and can be self-hosted; GPT-4o is proprietary.

Which is newer?

Aion-RP 1.0 (8B) is the newest, released Feb 4, 2025. Qwen2.5-VL 72B Instruct came out Jan 26, 2025; GPT-4o came out May 13, 2024. Knowledge cutoff: Aion-RP 1.0 (8B) Dec 31, 2023, GPT-4o Sep 2023, Qwen2.5-VL 72B Instruct Apr 2024.

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.