ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3-Next 80B-A3B (Thinking) vs Qwen3 Max vs Apertus 70B

Too close to call on our weighted score (Qwen3-Next 80B-A3B (Thinking) 34, Apertus 70B 33, Qwen3 Max 31). The right pick depends on what you value most.

  1. Alibaba (Qwen)

    Qwen3-Next 80B-A3B (Thinking)

    Released Sep 2025

    34/100
    • ECI—
    • Price$0.50 / $6.00
    • Context131K
    Full specs Remove Qwen3-Next 80B-A3B (Thinking)

  2. Alibaba (Qwen)

    Qwen3 Max

    Released Sep 23, 2025

    31/100
    • ECI142.4
    • Price$1.20 / $6.00
    • Context262K
    Full specs Remove Qwen3 Max

  3. Swiss AI

    Apertus 70B

    Released Sep 2, 2025

    33/100
    • ECI—
    • Price$0.82 / $2.42
    • Context66K
    Full specs Remove Apertus 70B
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 1 points (Qwen3-Next 80B-A3B (Thinking) 34/100, Apertus 70B 33/100, Qwen3 Max 31/100), so choose by what matters most for your work: Apertus 70B on price and Qwen3 Max for long inputs. 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-Next 80B-A3B (Thinking) $1.88 · Qwen3 Max $2.40 per 1M tokens (3:1 blend)
  • Longest contextQwen3 MaxQwen3 Max 262,144 · Qwen3-Next 80B-A3B (Thinking) 131,072 · Apertus 70B 65,536 tokens
  • Widest inputsSame inputsQwen3-Next 80B-A3B (Thinking): Text · Qwen3 Max: Text · Apertus 70B: Text
  • Self-hostingQwen3-Next 80B-A3B (Thinking) and Apertus 70BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightQwen3-Next 80B-A3B (Thinking)Qwen3 MaxApertus 70B
Price50%373246
Inputs & features30%352525
Context window20%243712
Overall100%34/10031/10033/100

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-Next 80B-A3B (Thinking) vs Qwen3 Max vs Apertus 70B specifications side by side
SpecificationQwen3-Next 80B-A3B (Thinking)Alibaba (Qwen)Qwen3 MaxAlibaba (Qwen)Apertus 70BSwiss AI
Capability
Capabilities Index (ECI)—142.4—
ECI rank—#91 of 148—
GPQA DiamondGraduate-level science questions—72.6%—
FrontierMath Tiers 1–3Research-level mathematics—19.0%—
OTIS Mock AIME 2024–2025Competition mathematics—73.3%—
SimpleQA VerifiedShort factual questions—48.8%—
Price per million tokens
Input$0.50 (best)$1.20$0.82
Output$6.00$6.00$2.42 (best)
Cached input———
Blended (3:1)$1.88$2.40$1.22 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIOfficial Alibaba APIMedian of 3 providers
Limits
Context window131,072 tokens262,144 tokens (best)65,536 tokens
Max output32,768 tokens65,536 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenProprietaryOpenApache-2.0
API model IDqwen3-next-80b-a3b-thinkingqwen3-max—
API providers1016 (best)3
ReleasedSep 2025Sep 23, 2025Sep 2, 2025
Knowledge cutoffApr 2025Apr 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-Next 80B-A3B (Thinking)$17.00
  • Qwen3 Max$24.00
  • Apertus 70B$13.04
04 — Questions

Which should you choose?

Which is better: Qwen3-Next 80B-A3B (Thinking), Qwen3 Max or Apertus 70B?

It is close. Our weighted score puts them within 1 points (Qwen3-Next 80B-A3B (Thinking) 34/100, Apertus 70B 33/100, Qwen3 Max 31/100), so choose by what matters most for your work: Apertus 70B on price and Qwen3 Max for long inputs. 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-Next 80B-A3B (Thinking), Qwen3 Max or Apertus 70B?

Apertus 70B is cheaper at $0.82 input / $2.42 output per million tokens (median across 3 API providers). Qwen3-Next 80B-A3B (Thinking) costs $0.50 input / $6.00 output per million tokens (official Alibaba API price); Qwen3 Max costs $1.20 input / $6.00 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $1.22 per million tokens for Apertus 70B versus $1.88 for Qwen3-Next 80B-A3B (Thinking) (1.5× as much) and $2.40 for Qwen3 Max (2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Qwen3-Next 80B-A3B (Thinking) has not been scored yet, Qwen3 Max has an ECI of 142.4 and Apertus 70B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3-Next 80B-A3B (Thinking), Qwen3 Max 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?

Qwen3 Max has the largest context window at 262,144 tokens, against 131,072 for Qwen3-Next 80B-A3B (Thinking) and 65,536 for Apertus 70B. Maximum output per response: Qwen3-Next 80B-A3B (Thinking) up to 32,768, Qwen3 Max up to 65,536, Apertus 70B up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Qwen3-Next 80B-A3B (Thinking) accepts text; Qwen3 Max accepts text; Apertus 70B accepts text. They handle the same number of input types.

Are any of these open source?

Qwen3-Next 80B-A3B (Thinking) and Apertus 70B publishes its weights (Apache-2.0) and can be self-hosted; Qwen3 Max is proprietary.

Which is newer?

Qwen3 Max is the newest, released Sep 23, 2025. Apertus 70B came out Sep 2, 2025; Qwen3-Next 80B-A3B (Thinking) came out Sep 2025. Knowledge cutoff: Qwen3-Next 80B-A3B (Thinking) Apr 2025, Qwen3 Max Apr 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons