ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Qwen3 VL 235B A22B Thinking vs DeepSeek R1 0528 vs Hermes 4 405B

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. Alibaba (Qwen)

    Qwen3 VL 235B A22B Thinking

    Released Sep 23, 2025

    45/100
    • ECI—
    • Price$0.50 / $3.95
    • Context131K
  2. DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    42/100
    • ECI140.8
    • Price$0.512 / $2.19
    • Context164K
  3. Nous Research

    Hermes 4 405B

    Released Aug 26, 2025

    37/100
    • ECI—
    • Price$1.00 / $3.00
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 VL 235B A22B Thinking 45/100, DeepSeek R1 0528 42/100, Hermes 4 405B 37/100) 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 priceDeepSeek R1 0528DeepSeek R1 0528 $0.932 · Qwen3 VL 235B A22B Thinking $1.36 · Hermes 4 405B $1.50 per 1M tokens (3:1 blend)
  • Longest contextDeepSeek R1 0528DeepSeek R1 0528 163,840 · Qwen3 VL 235B A22B Thinking 131,072 · Hermes 4 405B 131,072 tokens
  • Widest inputsQwen3 VL 235B A22B ThinkingQwen3 VL 235B A22B Thinking: Text, Images · DeepSeek R1 0528: Text · Hermes 4 405B: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightQwen3 VL 235B A22B ThinkingDeepSeek R1 0528Hermes 4 405B
Price50%424940
Inputs & features30%603535
Context window20%323632
Specs & price only100%45/10042/10037/100

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.

Qwen3 VL 235B A22B Thinking vs DeepSeek R1 0528 vs Hermes 4 405B specifications side by side
SpecificationQwen3 VL 235B A22B ThinkingAlibaba (Qwen)DeepSeek R1 0528DeepSeekHermes 4 405BNous Research
Capability
Capabilities Index (ECI)—140.8—
ECI rank—#113 of 158—
GPQA DiamondGraduate-level science questions—76.3%—
OTIS Mock AIME 2024–2025Competition mathematics—66.4%—
Price per million tokens
Input$0.50 (best)$0.512$1.00
Output$3.95$2.19 (best)$3.00
Cached input———
Blended (3:1)$1.36$0.932 (best)$1.50
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 5 providersMedian of 16 providersMedian of 4 providers
Limits
Context window131,072 tokens163,840 tokens (best)131,072 tokens
Max output32,768 tokens32,768 tokens117,964 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenMITOpen
API model ID———
API providers516 (best)4
ReleasedSep 23, 2025May 28, 2025Aug 26, 2025
Knowledge cutoffMar 31, 2025—Aug 31, 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.

  • Qwen3 VL 235B A22B Thinking$12.90
  • DeepSeek R1 0528$9.50
  • Hermes 4 405B$16.00
04 — Questions

Which should you choose?

Which is better: Qwen3 VL 235B A22B Thinking, DeepSeek R1 0528 or Hermes 4 405B?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 VL 235B A22B Thinking 45/100, DeepSeek R1 0528 42/100, Hermes 4 405B 37/100) 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, Qwen3 VL 235B A22B Thinking, DeepSeek R1 0528 or Hermes 4 405B?

DeepSeek R1 0528 is cheaper at $0.512 input / $2.19 output per million tokens (median across 16 API providers). Qwen3 VL 235B A22B Thinking costs $0.50 input / $3.95 output per million tokens (median across 5 API providers); Hermes 4 405B costs $1.00 input / $3.00 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $0.932 per million tokens for DeepSeek R1 0528 versus $1.36 for Qwen3 VL 235B A22B Thinking (1.5× as much) and $1.50 for Hermes 4 405B (1.6× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Qwen3 VL 235B A22B Thinking has not been scored yet, DeepSeek R1 0528 has an ECI of 140.8 and Hermes 4 405B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3 VL 235B A22B Thinking, DeepSeek R1 0528 and Hermes 4 405B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

DeepSeek R1 0528 has the largest context window at 163,840 tokens, against 131,072 for Qwen3 VL 235B A22B Thinking and 131,072 for Hermes 4 405B. Maximum output per response: Qwen3 VL 235B A22B Thinking up to 32,768, DeepSeek R1 0528 up to 32,768, Hermes 4 405B up to 117,964 tokens.

Which can read images, PDFs, audio or video?

Qwen3 VL 235B A22B Thinking accepts text and images; DeepSeek R1 0528 accepts text; Hermes 4 405B accepts text. Qwen3 VL 235B A22B Thinking handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (MIT), so you can self-host them.

Which is newer?

Qwen3 VL 235B A22B Thinking is the newest, released Sep 23, 2025. Hermes 4 405B came out Aug 26, 2025; DeepSeek R1 0528 came out May 28, 2025. Knowledge cutoff: Qwen3 VL 235B A22B Thinking Mar 31, 2025, Hermes 4 405B Aug 31, 2024.

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.