Qwen3.7-Max-PreviewvsDeepSeek-V4-Pro
Across 9 shared benchmarks, Qwen3.7-Max-Preview leads overall: Qwen3.7-Max-Preview wins 9, DeepSeek-V4-Pro wins 0, with 0 ties and an average score difference of +21.77.
Qwen3.7-Max-Preview
阿里巴巴 · 2026-05-20 · Reasoning model
DeepSeek-V4-Pro
DeepSeek-AI · 2026-04-24 · Reasoning model
Qwen3.7-Max-Preview9 wins(100%)(0%)0 winsDeepSeek-V4-Pro
Benchmark scores
Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.
Coding and Software Engineer
Qwen3.7-Max-Preview 4/4| Benchmark | Qwen3.7-Max-Preview | DeepSeek-V4-Pro | Diff |
|---|---|---|---|
| LiveCodeBench | 91.604 / 120最高（无工具） | 56.8075 / 120Normal (No Tools) | +34.80 |
| SWE-bench Multilingual | 78.303 / 20Thinking (With Tools) | 69.8015 / 20Normal (With Tools) | +8.50 |
| SWE-Bench Pro - Public | 60.606 / 44Thinking (With Tools) | 52.1029 / 44Normal (With Tools) | +8.50 |
| SWE-bench Verified | 80.4012 / 108Thinking (With Tools) | 73.6041 / 108Normal (With Tools) | +6.80 |
General Knowledge
Qwen3.7-Max-Preview 3/3| Benchmark | Qwen3.7-Max-Preview | DeepSeek-V4-Pro | Diff |
|---|---|---|---|
| HLE | 53.5012 / 161Thinking (With Tools) | 7.70145 / 161Normal (No Tools) | +45.80 |
| GPQA Diamond | 92.4011 / 179最高（无工具） | 72.90103 / 179Normal (No Tools) | +19.50 |
| MMLU Pro | 89.604 / 126最高（无工具） | 82.9046 / 126Normal (No Tools) | +6.70 |
AI Agent - Tool Usage
Qwen3.7-Max-Preview 1/1| Benchmark | Qwen3.7-Max-Preview | DeepSeek-V4-Pro | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 69.705 / 46Thinking (With Tools) | 59.1022 / 46Normal (With Tools) | +10.60 |
Math and Reasoning
Qwen3.7-Max-Preview 1/1| Benchmark | Qwen3.7-Max-Preview | DeepSeek-V4-Pro | Diff |
|---|---|---|---|
| IMO-AnswerBench | 902 / 20最高（无工具） | 35.3020 / 20Normal (No Tools) | +54.70 |
Specs
| Field | Qwen3.7-Max-Preview | DeepSeek-V4-Pro |
|---|---|---|
| Publisher | 阿里巴巴 | DeepSeek-AI |
| Release date | 2026-05-20 | 2026-04-24 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 1T | 1.6T |
| Context length | 1M | 1M |
| Max output | 64K | 375K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen3.7-Max-Preview | DeepSeek-V4-Pro |
|---|---|---|
| Text input | $2.5 / 1M tokens | $0.435 / 1M tokens |
| Text output | $7.5 / 1M tokens | $0.87 / 1M tokens |
| Cache read | $0.25 / 1M tokens | $0.87 / 1M tokens |
| Cache write | $3.125 / 1M tokens | $0.003625 / 1M tokens |
Summary
- Qwen3.7-Max-Previewleads in:Coding and Software Engineer (4/4), General Knowledge (3/3), AI Agent - Tool Usage (1/1), Math and Reasoning (1/1)
On average across the 9 shared benchmarks, Qwen3.7-Max-Preview scores 21.77 higher.
Largest single-benchmark gap: IMO-AnswerBench — Qwen3.7-Max-Preview 90 vs DeepSeek-V4-Pro 35.30 (+54.70).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.