See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
Qwen3.7-Max-Preview
阿里巴巴
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 指令跟随 +8.2 / Relative gap: none clear
Relative edge: none clear / Relative gap: 指令跟随 -8.2
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
Qwen3.7-Max-Preview · 82.37
Best single
Qwen3.7-Max-Preview · GPQA Diamond 92.40
Modality coverage
Qwen3.7-Max-Preview · 1 modalities
Head to head
7
Benchmarks
7
Wins
0
Losses
+5.39
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
7 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Qwen3.7-Max-Preview | Qwen3-Max-Thinking |
|---|---|---|
GPQA Diamond 综合评估 | 92.40Thinking Level · High | 87.40Thinking Enabled |
HLE 综合评估 | 53.50Thinking Enabled ｜ Tools | 49.80Thinking Enabled ｜ Tools |
MMLU Pro 综合评估 | 89.60Thinking Level · High | 85.70Thinking Enabled |
LiveCodeBench 编程与软件工程 | 91.60Thinking Level · High | 85.90Thinking Enabled |
SWE-bench Verified 编程与软件工程 | 80.40Thinking Enabled ｜ Tools | 75.30Thinking Enabled |
IF Bench 指令跟随 | 79.10Thinking Level · High | 70.90Thinking Enabled ｜ Tools |
IMO-AnswerBench 数学推理 | 90.00Thinking Level · High | 83.90Thinking Enabled |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Qwen3.7-Max-Preview阿里巴巴 | Qwen3-Max-Thinking阿里巴巴 |
|---|---|---|
Core specsRelease | 2026-05-20 | 2026-01-26 |
Context length | 1M | 1000K |
Parameters | 10000 | 10000 |
Max output | 65536 | 32768 |
MoE | Yes | Yes |
Supported modes | No mode data | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode） |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 不开源 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | Not provided | / |
Audio Input/Output | Not provided | / |
Video Input/Output | Not provided | / |
Embedding Input/Output | Not provided | / |
ResourcesPaper / report | Qwen3.7: The Agent Frontier | Qwen3-Max-Thinking: Pushing the Limits of Reasoning via Test-Time Scaling |
Qwen3-Max-Thinking
阿里巴巴
