ZMIME
Comparison · 2 models · Updated Nov 18, 2026

Claude Opus 4.6 vs Qwen3.7 Max

Claude Opus 4.6 comes out ahead, 80 to 72 on our weighted score, though Qwen3.7 Max is 2.7× cheaper per token.

Price in rating: Excluded · Include price

  1. Our pick

    Anthropic

    Claude Opus 4.6

    Released Feb 5, 2026

    80/100
    • ECI156.4
    • Price$5.00 / $25.00
    • Context1M
  2. Alibaba (Qwen)

    Qwen3.7 Max

    Released May 21, 2026

    72/100
    • ECI154.6
    • Price$2.50 / $7.50
    • Context1M
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Claude Opus 4.6 is our pick

Claude Opus 4.6 is the better all-round choice, scoring 80/100 against Qwen3.7 Max (72). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityClaude Opus 4.6Capabilities Index (ECI): Claude Opus 4.6 156.4 · Qwen3.7 Max 154.6
  • Lowest priceQwen3.7 MaxQwen3.7 Max $3.75 · Claude Opus 4.6 $10.00 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameClaude Opus 4.6 1,000,000 · Qwen3.7 Max 1,000,000 tokens
  • Widest inputsClaude Opus 4.6Claude Opus 4.6: Text, Images, PDFs · Qwen3.7 Max: Text
  • Self-hostingNo confirmed open weightsBoth are available only through APIs
How the score is built
MeasureWeightClaude Opus 4.6Qwen3.7 Max
CapabilityCapabilities Index (ECI)67%8382
Inputs & features20%8045
Context window13%6464
Overall100%80/10072/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Claude Opus 4.6 vs Qwen3.7 Max specifications side by side
SpecificationClaude Opus 4.6AnthropicQwen3.7 MaxAlibaba (Qwen)
Capability
Capabilities Index (ECI)156.4 (best)154.6
ECI rank#39 of 158 (best)#49 of 158
GPQA DiamondGraduate-level science questions90.5%90.9% (best)
FrontierMath Tiers 1–3Research-level mathematics66.0% (best)64.6%
OTIS Mock AIME 2024–2025Competition mathematics94.4%95.6% (best)
SWE-bench VerifiedFixing real GitHub issues78.7% (best)77.3%
SimpleQA VerifiedShort factual questions47.0%55.8% (best)
Price per million tokens
Input$5.00$2.50 (best)
Output$25.00$7.50 (best)
Cached input$0.50$0.50
Blended (3:1)$10.00$3.75 (best)
Long-context rateSame rateSame rate
Price sourceOfficial Anthropic APIOfficial Alibaba API
Limits
Context window1,000,000 tokens1,000,000 tokens
Max output128,000 tokens131,072 tokens (best)
Inputs and features
TextYesYes
ImagesYesNo
PDFsYesNo
AudioNoNo
VideoNoNo
ReasoningYeslow · medium · high · maxYes
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDclaude-opus-4-6qwen3.7-max
API providers45 (best)31
ReleasedFeb 5, 2026May 21, 2026
Knowledge cutoffMay 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 Opus 4.6$100.00
  • Qwen3.7 Max$40.00
04 — Questions

Which should you choose?

Which is better: Claude Opus 4.6 or Qwen3.7 Max?

Claude Opus 4.6 is the better all-round choice, scoring 80/100 against Qwen3.7 Max (72). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Claude Opus 4.6 or Qwen3.7 Max?

Qwen3.7 Max is cheaper at $2.50 input / $7.50 output per million tokens (official Alibaba API price). Claude Opus 4.6 costs $5.00 input / $25.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $3.75 per million tokens for Qwen3.7 Max versus $10.00 for Claude Opus 4.6 (2.7× as much).

Which scores higher on benchmarks?

Claude Opus 4.6 scores higher on the Capabilities Index (ECI): Claude Opus 4.6 156.4 (#39 of 158) and Qwen3.7 Max 154.6 (#49 of 158). The confidence ranges of the top two overlap (154.6–158.3 vs 152.6–156.7), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen3.7 Max 90.9%, Claude Opus 4.6 90.5%; FrontierMath Tiers 1–3 — Claude Opus 4.6 66.0%, Qwen3.7 Max 64.6%; OTIS Mock AIME 2024–2025 — Qwen3.7 Max 95.6%, Claude Opus 4.6 94.4%; SWE-bench Verified — Claude Opus 4.6 78.7%, Qwen3.7 Max 77.3%; SimpleQA Verified — Qwen3.7 Max 55.8%, Claude Opus 4.6 47.0%.

Which is better for coding?

Claude Opus 4.6 resolves more real GitHub issues on SWE-bench Verified: Claude Opus 4.6 78.7% and Qwen3.7 Max 77.3%. Both support tool calling for agent workflows.

Which has the bigger context window?

Claude Opus 4.6 and Qwen3.7 Max share the same 1,000,000-token context window. Maximum output per response: Claude Opus 4.6 up to 128,000, Qwen3.7 Max up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Claude Opus 4.6 accepts text, images and PDFs; Qwen3.7 Max accepts text. Claude Opus 4.6 handles the widest range of inputs.

Are any of these open source?

No. Claude Opus 4.6 and Qwen3.7 Max are proprietary and only available through APIs and apps.

Which is newer?

Qwen3.7 Max is the newest, released May 21, 2026. Claude Opus 4.6 came out Feb 5, 2026. Knowledge cutoff: Claude Opus 4.6 May 31, 2025.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.