ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Haiku 4.5 vs Hermes 4 405B vs Qwen3 VL 235B A22B Thinking

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

Price in rating: Excluded · Include price

  1. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    64/100
    • ECI142.8
    • Price$1.00 / $5.00
    • Context200K
  2. Nous Research

    Hermes 4 405B

    Released Aug 26, 2025

    34/100
    • ECI—
    • Price$1.00 / $3.00
    • Context131K
  3. Alibaba (Qwen)

    Qwen3 VL 235B A22B Thinking

    Released Sep 23, 2025

    49/100
    • ECI—
    • Price$0.50 / $3.95
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Claude Haiku 4.5 64/100, Qwen3 VL 235B A22B Thinking 49/100, Hermes 4 405B 34/100) 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 priceQwen3 VL 235B A22B ThinkingQwen3 VL 235B A22B Thinking $1.36 · Hermes 4 405B $1.50 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
  • Longest contextClaude Haiku 4.5Claude Haiku 4.5 200,000 · Hermes 4 405B 131,072 · Qwen3 VL 235B A22B Thinking 131,072 tokens
  • Widest inputsClaude Haiku 4.5Claude Haiku 4.5: Text, Images, PDFs · Hermes 4 405B: Text · Qwen3 VL 235B A22B Thinking: Text, Images
  • Self-hostingHermes 4 405B and Qwen3 VL 235B A22B ThinkingPublishes downloadable weights
How the score is built
MeasureWeightClaude Haiku 4.5Hermes 4 405BQwen3 VL 235B A22B Thinking
Inputs & features60%803560
Context window40%393232
Specs only100%64/10034/10049/100

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.

Claude Haiku 4.5 vs Hermes 4 405B vs Qwen3 VL 235B A22B Thinking specifications side by side
SpecificationClaude Haiku 4.5AnthropicHermes 4 405BNous ResearchQwen3 VL 235B A22B ThinkingAlibaba (Qwen)
Capability
Capabilities Index (ECI)142.8——
ECI rank#102 of 158——
GPQA DiamondGraduate-level science questions71.2%——
OTIS Mock AIME 2024–2025Competition mathematics66.7%——
SimpleQA VerifiedShort factual questions13.2%——
Price per million tokens
Input$1.00$1.00$0.50 (best)
Output$5.00$3.00 (best)$3.95
Cached input$0.10——
Blended (3:1)$2.00$1.50$1.36 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Anthropic APIMedian of 4 providersMedian of 5 providers
Limits
Context window200,000 tokens (best)131,072 tokens131,072 tokens
Max output64,000 tokens117,964 tokens (best)32,768 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenOpen
API model IDclaude-haiku-4-5——
API providers57 (best)45
ReleasedOct 15, 2025Aug 26, 2025Sep 23, 2025
Knowledge cutoffFeb 28, 2025Aug 31, 2024Mar 31, 2025
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.

  • Claude Haiku 4.5$20.00
  • Hermes 4 405B$16.00
  • Qwen3 VL 235B A22B Thinking$12.90
04 — Questions

Which should you choose?

Which is better: Claude Haiku 4.5, Hermes 4 405B or Qwen3 VL 235B A22B Thinking?

There is not enough shared capability evidence to name an overall winner. The scores (Claude Haiku 4.5 64/100, Qwen3 VL 235B A22B Thinking 49/100, Hermes 4 405B 34/100) 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, Claude Haiku 4.5, Hermes 4 405B or Qwen3 VL 235B A22B Thinking?

Qwen3 VL 235B A22B Thinking is cheaper at $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); Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $1.36 per million tokens for Qwen3 VL 235B A22B Thinking versus $1.50 for Hermes 4 405B (1.1× as much) and $2.00 for Claude Haiku 4.5 (1.5× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Claude Haiku 4.5 has an ECI of 142.8, Hermes 4 405B has not been scored yet and Qwen3 VL 235B A22B Thinking has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 4.5, Hermes 4 405B and Qwen3 VL 235B A22B Thinking 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?

Claude Haiku 4.5 has the largest context window at 200,000 tokens, against 131,072 for Hermes 4 405B and 131,072 for Qwen3 VL 235B A22B Thinking. Maximum output per response: Claude Haiku 4.5 up to 64,000, Hermes 4 405B up to 117,964, Qwen3 VL 235B A22B Thinking up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Claude Haiku 4.5 accepts text, images and PDFs; Hermes 4 405B accepts text; Qwen3 VL 235B A22B Thinking accepts text and images. Claude Haiku 4.5 handles the widest range of inputs.

Are any of these open source?

Hermes 4 405B and Qwen3 VL 235B A22B Thinking publishes its weights and can be self-hosted; Claude Haiku 4.5 is proprietary.

Which is newer?

Claude Haiku 4.5 is the newest, released Oct 15, 2025. Qwen3 VL 235B A22B Thinking came out Sep 23, 2025; Hermes 4 405B came out Aug 26, 2025. Knowledge cutoff: Claude Haiku 4.5 Feb 28, 2025, Hermes 4 405B Aug 31, 2024, Qwen3 VL 235B A22B Thinking Mar 31, 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.