Qwen3.7-Max-PreviewvsKimi K2.6
Across 8 shared benchmarks, Qwen3.7-Max-Preview leads overall: Qwen3.7-Max-Preview wins 7, Kimi K2.6 wins 1, with 0 ties and an average score difference of +1.78.
Qwen3.7-Max-Preview
阿里巴巴 · 2026-05-20 · Reasoning model
Kimi K2.6
Moonshot AI · 2026-04-20 · Reasoning model
Qwen3.7-Max-Preview7 wins(88%)(13%)1 winKimi K2.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
Coding and Software Engineer
Qwen3.7-Max-Preview 4/4| Benchmark | Qwen3.7-Max-Preview | Kimi K2.6 | Diff |
|---|---|---|---|
| LiveCodeBench | 91.604 / 120最高（无工具） | 89.607 / 120Thinking (No Tools) | +2 |
| SWE-Bench Pro - Public | 60.606 / 44Thinking (With Tools) | 58.608 / 44Thinking (With Tools) | +2 |
| SWE-bench Multilingual | 78.303 / 20Thinking (With Tools) | 76.704 / 20Thinking (With Tools) | +1.60 |
| SWE-bench Verified | 80.4012 / 108Thinking (With Tools) | 80.2013 / 108Thinking (With Tools) | +0.20 |
General Knowledge
Even 2/2| Benchmark | Qwen3.7-Max-Preview | Kimi K2.6 | Diff |
|---|---|---|---|
| GPQA Diamond | 92.4011 / 179最高（无工具） | 90.5017 / 179Thinking (No Tools) | +1.90 |
| HLE | 53.5012 / 161Thinking (With Tools) | 5411 / 161Thinking (With Tools + Internet) | -0.50 |
AI Agent - Tool Usage
Qwen3.7-Max-Preview 1/1| Benchmark | Qwen3.7-Max-Preview | Kimi K2.6 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 69.705 / 46Thinking (With Tools) | 66.7010 / 46Thinking (With Tools) | +3 |
Math and Reasoning
Qwen3.7-Max-Preview 1/1| Benchmark | Qwen3.7-Max-Preview | Kimi K2.6 | Diff |
|---|---|---|---|
| IMO-AnswerBench | 902 / 20最高（无工具） | 867 / 20Thinking (No Tools) | +4 |
Specs
| Field | Qwen3.7-Max-Preview | Kimi K2.6 |
|---|---|---|
| Publisher | 阿里巴巴 | Moonshot AI |
| Release date | 2026-05-20 | 2026-04-20 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 1T | 1T |
| Context length | 1M | 256K |
| Max output | 64K | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen3.7-Max-Preview | Kimi K2.6 |
|---|---|---|
| Text input | $2.5 / 1M tokens | $0.95 / 1M tokens |
| Text output | $7.5 / 1M tokens | $4 / 1M tokens |
| Cache read | $0.25 / 1M tokens | $0.16 / 1M tokens |
| Cache write | $3.125 / 1M tokens | $0.95 / 1M tokens |
Summary
- Qwen3.7-Max-Previewleads in:Coding and Software Engineer (4/4), AI Agent - Tool Usage (1/1), Math and Reasoning (1/1)
- Tied in:General Knowledge
On average across the 8 shared benchmarks, Qwen3.7-Max-Preview scores 1.78 higher.
Largest single-benchmark gap: IMO-AnswerBench — Qwen3.7-Max-Preview 90 vs Kimi K2.6 86 (+4).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.