Qwen3.7-Max-PreviewvsQwen3.6-Max-Preview
Across 10 shared benchmarks, Qwen3.7-Max-Preview leads overall: Qwen3.7-Max-Preview wins 10, Qwen3.6-Max-Preview wins 0, with 0 ties and an average score difference of +3.57.
Qwen3.7-Max-Preview
阿里巴巴 · 2026-05-20 · Reasoning model
Qwen3.6-Max-Preview
阿里巴巴 · 2026-04-20 · Chat model
Qwen3.7-Max-Preview10 wins(100%)(0%)0 winsQwen3.6-Max-Preview
Benchmark scores
Grouped by capability, sorted by largest gap within each. 10 shared benchmarks.
Coding and Software Engineer
Qwen3.7-Max-Preview 4/4| Benchmark | Qwen3.7-Max-Preview | Qwen3.6-Max-Preview | Diff |
|---|---|---|---|
| LiveCodeBench | 91.604 / 120最高（无工具） | 87.1010 / 120最高（无工具） | +4.50 |
| SWE-bench Multilingual | 78.303 / 20Thinking (With Tools) | 73.807 / 20Thinking (With Tools) | +4.50 |
| SWE-Bench Pro - Public | 60.606 / 44Thinking (With Tools) | 57.3012 / 44Deep Thinking (With Tools) | +3.30 |
| SWE-bench Verified | 80.4012 / 108Thinking (With Tools) | 78.8020 / 108Thinking (With Tools) | +1.60 |
General Knowledge
Qwen3.7-Max-Preview 3/3| Benchmark | Qwen3.7-Max-Preview | Qwen3.6-Max-Preview | Diff |
|---|---|---|---|
| HLE | 53.5012 / 161Thinking (With Tools) | 50.2022 / 161Thinking (With Tools) | +3.30 |
| GPQA Diamond | 92.4011 / 179最高（无工具） | 90.4018 / 179最高（无工具） | +2 |
| MMLU Pro | 89.604 / 126最高（无工具） | 88.505 / 126最高（无工具） | +1.10 |
AI Agent - Tool Usage
Qwen3.7-Max-Preview 1/1| Benchmark | Qwen3.7-Max-Preview | Qwen3.6-Max-Preview | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 69.705 / 46Thinking (With Tools) | 65.4011 / 46Deep Thinking (With Tools) | +4.30 |
Instruction Following
Qwen3.7-Max-Preview 1/1| Benchmark | Qwen3.7-Max-Preview | Qwen3.6-Max-Preview | Diff |
|---|---|---|---|
| IF Bench | 79.102 / 29最高（无工具） | 74.206 / 29最高（无工具） | +4.90 |
Math and Reasoning
Qwen3.7-Max-Preview 1/1| Benchmark | Qwen3.7-Max-Preview | Qwen3.6-Max-Preview | Diff |
|---|---|---|---|
| IMO-AnswerBench | 902 / 20最高（无工具） | 83.8011 / 20最高（无工具） | +6.20 |
Specs
| Field | Qwen3.7-Max-Preview | Qwen3.6-Max-Preview |
|---|---|---|
| Publisher | 阿里巴巴 | 阿里巴巴 |
| Release date | 2026-05-20 | 2026-04-20 |
| Model type | Reasoning model | Chat model |
| Architecture | MoE | MoE |
| Parameters | 1T | 1T |
| Context length | 1M | 262K |
| Max output | 64K | 8K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen3.7-Max-Preview | Qwen3.6-Max-Preview |
|---|---|---|
| Text input | $2.5 / 1M tokens | $1.3 / 1M tokens |
| Text output | $7.5 / 1M tokens | $7.8 / 1M tokens |
| Cache read | $0.25 / 1M tokens | Not public |
| Cache write | $3.125 / 1M tokens | Not public |
Summary
- Qwen3.7-Max-Previewleads in:Coding and Software Engineer (4/4), General Knowledge (3/3), AI Agent - Tool Usage (1/1), Instruction Following (1/1), Math and Reasoning (1/1)
On average across the 10 shared benchmarks, Qwen3.7-Max-Preview scores 3.57 higher.
Largest single-benchmark gap: IMO-AnswerBench — Qwen3.7-Max-Preview 90 vs Qwen3.6-Max-Preview 83.80 (+6.20).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.