Qwen3 Max Thinking vs Qwen3.7 Max

Qwen3.7 Max leads the LLM Stats Score 45.6 to 33.0. Qwen3.7 Max is 1.3x cheaper per token.

Alibaba Cloud / Qwen Team · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Qwen3.7 Max leads the overall LLM Stats Score 45.6 to 33.0, ranking #26 overall.

In the 19 individual benchmarks reported for both models, Qwen3.7 Max wins 19; this is a narrower head-to-head signal than the composite indexes.

On price, Qwen3.7 Max is roughly 1.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Qwen3.7 Max also accepts a larger context window (1,000,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Qwen3 Max Thinking

you want predictable pricing at $1.20/M input and $6.00/M output

Choose Qwen3.7 Max

overall performance matters — it scores 45.6 and ranks #26 on LLM Stats
your work emphasizes reasoning and coding — it leads those capability indexes
you value its reported benchmark strengths — it wins 19 of 19 exact shared results
cost matters — it's about 1.3x cheaper per token
you process long inputs — it offers a 1,000,000 token context window
you want the most recent training data — it shipped May 2026

At a glance

The differences that matter most.

Better token value: Qwen3.7 Max

Qwen3 Max Thinking

Alibaba Cloud / Qwen Team

Qwen3.7 Max

Alibaba Cloud / Qwen Team

Core performance indexes

LLM Stats Score

33.0

#101 · 33 evals

45.6

#26 · 37 evals

Best

Reasoning

34.1

#90 · 26 evals

46.2

#25 · 24 evals

Best

Coding

16.4

#124 · 3 evals

36.3

#21 · 10 evals

Best

Agents

10.3

#115 · 8 evals

29.3

#36 · 13 evals

Best

Cost, coverage & limits

Benchmark wins

0 of 19

19 of 19

Best

Input price

$1.20 / M

Best

$1.25 / M

Output price

$6.00 / M

$3.75 / M

Best

Context window

256,000

1,000,000

Best

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared

Index

Qwen3 Max Thinking

Qwen3.7 Max

Math

32.2#62 · 8 evals

43.1#3 · 13 evals

Tool use

3.5#161 · 4 evals

27.5#22 · 5 evals

Finance

32.7#12 · 2 evals

41.1#1 · 4 evals

Legal

32.7#12 · 2 evals

44.5#1 · 3 evals

Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

34 reported for Qwen3 Max Thinking · 42 for Qwen3.7 Max

19 shared

Qwen3 Max Thinking outperforms in 0 benchmarks, while Qwen3.7 Max is better at 19 benchmarks (BFCL-V4, Global PIQA, GPQA, IFBench, IFEval, IMO-AnswerBench, LiveCodeBench v6, MAXIFE, MCP-Mark, MMLU-Pro, MMLU-Redux, MMMLU, NOVA-63, SuperGPQA, SWE-bench Multilingual, SWE-Bench Verified, Terminal-Bench 2.0, VITA-Bench, WMT24++).

Qwen3.7 Max significantly outperforms across most benchmarks.

Wed Sep 09 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Qwen3.7 Max costs less

For input processing, Qwen3 Max Thinking ($1.20/1M tokens) is 1.0x cheaper than Qwen3.7 Max ($1.25/1M tokens).

For output processing, Qwen3 Max Thinking ($6.00/1M tokens) is 1.6x more expensive than Qwen3.7 Max ($3.75/1M tokens).

In conclusion, Qwen3 Max Thinking is more expensive than Qwen3.7 Max.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers

Wed Sep 09 2026 • llm-stats.com

Qwen3 Max Thinking

Input tokens$1.20

Output tokens$6.00

Best providerDeepinfra

Qwen3.7 Max

Input tokens$1.25

Output tokens$3.75

Best providerNovita

Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Qwen3.7 Max accepts 1,000,000 input tokens compared to Qwen3 Max Thinking's 256,000 tokens. Qwen3 Max Thinking can generate longer responses up to 256,000 tokens, while Qwen3.7 Max is limited to 65,536 tokens.

Qwen3 Max Thinking

Input256,000 tokens

Output256,000 tokens

Qwen3.7 Max

Input1,000,000 tokens

Output65,536 tokens

Wed Sep 09 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Qwen3 Max Thinking

Proprietary

Closed source

Qwen3.7 Max

Proprietary

Closed source

Release Timeline

When each model was launched

Qwen3 Max Thinking was released on 2026-02-13, while Qwen3.7 Max was released on 2026-05-19.

Qwen3.7 Max is 3 months newer than Qwen3 Max Thinking.

Qwen3 Max Thinking

Feb 13, 2026

6 months ago

Qwen3.7 Max

May 19, 2026

3 months ago

3mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Qwen3 Max Thinking is available from DeepInfra. Qwen3.7 Max is available from Novita, DeepInfra, Together.

Qwen3 Max Thinking

Deepinfra

Input Price:Input: $1.20/1MOutput Price:Output: $6.00/1M

Qwen3.7 Max

Novita

Input Price:Input: $1.25/1MOutput Price:Output: $3.75/1M

Deepinfra

Input Price:Input: $2.50/1MOutput Price:Output: $7.50/1M

Together

Input Price:Input: $2.50/1MOutput Price:Output: $7.50/1M

* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Qwen3 Max Thinking and Qwen3.7 Max side-by-side, then vote on the output you prefer.

Qwen3 Max Thinking

✓ Preferred

Qwen3.7 Max

Open in Playground

FAQ

Common questions about Qwen3 Max Thinking vs Qwen3.7 Max.

Which is better, Qwen3 Max Thinking or Qwen3.7 Max?

Qwen3.7 Max leads the LLM Stats Score 45.6 to 33.0. Qwen3 Max Thinking is made by Alibaba Cloud / Qwen Team and Qwen3.7 Max is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Qwen3 Max Thinking compare to Qwen3.7 Max in benchmarks?

Qwen3 Max Thinking scores C-Eval: 93.7%, IFEval: 93.4%, AIME 2026: 93.3%, MMLU-Redux: 92.8%, GPQA: 87.4%. Qwen3.7 Max scores HMMT Feb 26: 97.1%, Kernel Bench L3: 96.0%, MMLU-Redux: 95.0%, IFEval: 94.3%, GPQA: 92.4%.

Is Qwen3 Max Thinking cheaper than Qwen3.7 Max?

Qwen3 Max Thinking is 1.0x cheaper for input tokens. Qwen3 Max Thinking costs $1.20/M input and $6.00/M output via deepinfra. Qwen3.7 Max costs $1.25/M input and $3.75/M output via novita.

What are the context window sizes for Qwen3 Max Thinking and Qwen3.7 Max?

Qwen3 Max Thinking supports 256K tokens and Qwen3.7 Max supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Qwen3 Max Thinking and Qwen3.7 Max?

Key differences include LLM Stats Score (33.0 vs 45.6), context window (256K vs 1.0M), input pricing ($1.20 vs $1.25/M). See the full comparison above for benchmark-by-benchmark results.

Qwen3 Max Thinking vs Qwen3.7 Max