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。
DeepSeek-V4-Pro
DeepSeek-AI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: none clear / Relative gap: 数学推理 -19.0
Relative edge: 数学推理 +19.0 / Relative gap: none clear
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 · 78.46
Best single
DeepSeek-V4-Pro · LiveCodeBench 93.50
Modality coverage
DeepSeek-V4-Pro · 1 modalities
Head to head
9
Benchmarks
2
Wins
7
Losses
-1.88
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.
9 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | DeepSeek-V4-Pro | Qwen3.7-Max-Preview |
|---|---|---|
HLE 综合评估 | 48.20Thinking Level · Extra High ｜ Tools | 53.50Thinking Enabled ｜ Tools |
MMLU Pro 综合评估 | 87.50Thinking Level · High | 89.60Thinking Level · High |
GPQA Diamond 科学与综合推理 | 90.10Thinking Level · High | 92.40Thinking Level · High |
LiveCodeBench 编程与软件工程 | 93.50Thinking Level · High | 91.60Thinking Level · High |
SWE-bench Multilingual 编程与软件工程 | 76.20Thinking Level · Extra High ｜ Tools | 78.30Thinking Enabled ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 55.40Thinking Level · Extra High ｜ Tools | 60.60Thinking Enabled ｜ Tools |
SWE-bench Verified 编程与软件工程 | 80.60Thinking Level · Extra High ｜ Tools | 80.40Thinking Enabled ｜ Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 67.90Thinking Level · Extra High ｜ Tools | 69.70Thinking Enabled ｜ Tools |
IMO-AnswerBench 数学推理 | 89.80Thinking Level · High | 90.00Thinking Level · High |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | DeepSeek-V4-ProDeepSeek-AI | Qwen3.7-Max-Preview阿里巴巴 |
|---|---|---|
Core specsRelease | 2026-08-13 | 2026-05-20 |
Context length | 1M | 1M |
Parameters | 16000 | — |
Active parameters | 490 | Not provided |
Max output | 384000 | 65536 |
MoE | Yes | No |
LicenseCode Open Source | Closed Source | Not provided |
Weights Open Source | Closed Source | Not provided |
Commercial use | 免费商用授权 | 不开源 |
Modality supportText Input/Output | / | / |
ResourcesPaper / report | DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence | Qwen3.7: The Agent Frontier |
Qwen3.7-Max-Preview
阿里巴巴
