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。

Kimi K2.6
Moonshot AI

Qwen3.7 Max
阿里巴巴
Each axis is a category average, normalized to a 100-point radar.
Relative edge: none clear / Relative gap: AI Agent - 工具使用 -5.0
Relative edge: AI Agent - 工具使用 +5.0 / 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 · 76.72
Best single
Qwen3.7 Max · GPQA Diamond 92.40
Modality coverage
Kimi K2.6 · 3 modalities
Head to head
10
Benchmarks
1
Wins
9
Losses
-2.33
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.
10 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Kimi K2.6 | Qwen3.7 Max |
|---|---|---|
HLE 综合评估 | 54.00Thinking Enabled | Tools | 53.50Thinking Enabled | Tools |
LiveBench 综合评估 | 72.17Thinking Enabled | 74.29Deep Thinking Mode |
GPQA Diamond 科学与综合推理 | 90.50Thinking Enabled | 92.40Thinking Level · High |
LiveCodeBench 编程与软件工程 | 89.60Thinking Enabled | 91.60Thinking Level · High |
SWE-bench Multilingual 编程与软件工程 | 76.70Thinking Enabled | Tools | 78.30Thinking Enabled | Tools |
SWE-Bench Pro - Public 编程与软件工程 | 58.60Thinking Enabled | Tools | 60.60Thinking Enabled | Tools |
SWE-bench Verified 编程与软件工程 | 80.20Thinking Enabled | Tools | 80.40Thinking Enabled | Tools |
MCP-Atlas AI Agent - 工具使用 | 69.40Thinking Enabled | Tools | 76.40Thinking Enabled | Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 66.70Thinking Enabled | Tools | 69.70Thinking Enabled | Tools |
IMO-AnswerBench 数学推理 | 86.00Thinking Enabled | 90.00Thinking Level · High |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Kimi K2.6Moonshot AI | Qwen3.7 Max阿里巴巴 |
|---|---|---|
Core specsRelease | 2026-04-20 | 2026-05-20 |
Context length | 256K | 1M |
Parameters | 1T | — |
Active parameters | 32B | Not provided |
Max output | Not provided | 65536 |
MoE | Yes | No |
Supported modes | 常规模式(Non-Thinking Mode)思考模式(Thinking Mode) | No mode data |
LicenseCode Open Source | Open Source · Modified MIT | Closed Source |
Weights Open Source | Open Source · Modified MIT | Closed Source |
Commercial use | 免费商用授权 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | Not provided |
Video Input/Output | / | Not provided |
ResourcesPaper / report | Kimi K2.6: Advancing Open-Source Coding | Qwen3.7: The Agent Frontier |