ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Qwen3 VL 235B A22B Thinking vs Gemini 2.5 Pro Preview 06-05 vs Apertus 70B

Gemini 2.5 Pro Preview 06-05 comes out ahead, 48 to 44 and 32 on our weighted score, though Apertus 70B is 2.7× cheaper per token.

  1. Alibaba (Qwen)

    Qwen3 VL 235B A22B Thinking

    Released Sep 23, 2025

    44/100
    • ECI—
    • Price$0.50 / $3.95
    • Context131K
    Full specs Remove Qwen3 VL 235B A22B Thinking
  2. Our pick

    Google

    Gemini 2.5 Pro Preview 06-05

    Released Jun 5, 2025

    48/100
    • ECI—
    • Price$1.22 / $9.75
    • Context1.05M
    Full specs Remove Gemini 2.5 Pro Preview 06-05

  3. Swiss AI

    Apertus 70B

    Released Sep 2, 2025

    32/100
    • ECI—
    • Price$0.82 / $2.42
    • Context66K
    Full specs Remove Apertus 70B
01 — Verdict

Gemini 2.5 Pro Preview 06-05 is our pick

Gemini 2.5 Pro Preview 06-05 is the better all-round choice, scoring 48/100 against Qwen3 VL 235B A22B Thinking (44) and Apertus 70B (32). It leads on inputs & features and context window. Apertus 70B wins on 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 priceApertus 70BApertus 70B $1.22 · Qwen3 VL 235B A22B Thinking $1.36 · Gemini 2.5 Pro Preview 06-05 $3.35 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 Pro Preview 06-05Gemini 2.5 Pro Preview 06-05 1,048,576 · Qwen3 VL 235B A22B Thinking 131,072 · Apertus 70B 65,536 tokens
  • Widest inputsGemini 2.5 Pro Preview 06-05Qwen3 VL 235B A22B Thinking: Text, Images · Gemini 2.5 Pro Preview 06-05: Text, Images, PDFs, Audio · Apertus 70B: Text
  • Self-hostingQwen3 VL 235B A22B Thinking and Apertus 70BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightQwen3 VL 235B A22B ThinkingGemini 2.5 Pro Preview 06-05Apertus 70B
Price50%422444
Inputs & features30%608025
Context window20%256112
Overall100%44/10048/10032/100

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 Gemini 2.5 Pro Preview 06-05 vs Apertus 70B specifications side by side
SpecificationQwen3 VL 235B A22B ThinkingAlibaba (Qwen)Gemini 2.5 Pro Preview 06-05GoogleApertus 70BSwiss AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50 (best)$1.22$0.82
Output$3.95$9.75$2.42 (best)
Cached input———
Blended (3:1)$1.36$3.35$1.22 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 5 providersMedian of 4 providersMedian of 3 providers
Limits
Context window131,072 tokens1,048,576 tokens (best)65,536 tokens
Max output32,768 tokens65,536 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoYesNo
AudioNoYesNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenProprietaryOpenApache-2.0
API model ID———
API providers5 (best)43
ReleasedSep 23, 2025Jun 5, 2025Sep 2, 2025
Knowledge cutoffMar 31, 2025Jan 31, 2025Sep 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.

  • Qwen3 VL 235B A22B Thinking$12.90
  • Gemini 2.5 Pro Preview 06-05$31.69
  • Apertus 70B$13.04
04 — Questions

Which should you choose?

Which is better: Qwen3 VL 235B A22B Thinking, Gemini 2.5 Pro Preview 06-05 or Apertus 70B?

Gemini 2.5 Pro Preview 06-05 is the better all-round choice, scoring 48/100 against Qwen3 VL 235B A22B Thinking (44) and Apertus 70B (32). It leads on inputs & features and context window. Apertus 70B wins on 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, Gemini 2.5 Pro Preview 06-05 or Apertus 70B?

Apertus 70B is cheaper at $0.82 input / $2.42 output per million tokens (median across 3 API providers). Qwen3 VL 235B A22B Thinking costs $0.50 input / $3.95 output per million tokens (median across 5 API providers); Gemini 2.5 Pro Preview 06-05 costs $1.22 input / $9.75 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $1.22 per million tokens for Apertus 70B versus $1.36 for Qwen3 VL 235B A22B Thinking (1.1× as much) and $3.35 for Gemini 2.5 Pro Preview 06-05 (2.7× 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, Gemini 2.5 Pro Preview 06-05 has not been scored yet and Apertus 70B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3 VL 235B A22B Thinking, Gemini 2.5 Pro Preview 06-05 and Apertus 70B 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?

Gemini 2.5 Pro Preview 06-05 has the largest context window at 1,048,576 tokens, against 131,072 for Qwen3 VL 235B A22B Thinking and 65,536 for Apertus 70B. Maximum output per response: Qwen3 VL 235B A22B Thinking up to 32,768, Gemini 2.5 Pro Preview 06-05 up to 65,536, Apertus 70B up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Qwen3 VL 235B A22B Thinking accepts text and images; Gemini 2.5 Pro Preview 06-05 accepts text, images, PDFs and audio; Apertus 70B accepts text. Gemini 2.5 Pro Preview 06-05 handles the widest range of inputs.

Are any of these open source?

Qwen3 VL 235B A22B Thinking and Apertus 70B publishes its weights (Apache-2.0) and can be self-hosted; Gemini 2.5 Pro Preview 06-05 is proprietary.

Which is newer?

Qwen3 VL 235B A22B Thinking is the newest, released Sep 23, 2025. Apertus 70B came out Sep 2, 2025; Gemini 2.5 Pro Preview 06-05 came out Jun 5, 2025. Knowledge cutoff: Qwen3 VL 235B A22B Thinking Mar 31, 2025, Gemini 2.5 Pro Preview 06-05 Jan 31, 2025, Apertus 70B Sep 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 2, 2026.

05 — Keep comparing

Related comparisons