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
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 综合评估 +2.2 / Relative gap: AI Agent - 工具使用 -4.7
Relative edge: AI Agent - 工具使用 +4.7 / Relative gap: 综合评估 -2.2
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
MiniMax M3 · 70.45
Best single
MiniMax M3 · BrowseComp 83.50
Modality coverage
Kimi K2.6 · 3 modalities
Head to head
6
Benchmarks
2
Wins
4
Losses
-2.11
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.
6 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Kimi K2.6 | MiniMax M3 |
|---|---|---|
LiveBench 综合评估 | 72.17Thinking Enabled | 70.02Deep Thinking Mode |
SWE-Bench Pro - Public 编程与软件工程 | 58.60Thinking Enabled | Tools | 59.00Thinking Enabled | Tools |
BrowseComp AI Agent - 信息收集 | 83.20Thinking Enabled | Tools | 83.50Thinking Enabled | Tools |
MCP-Atlas AI Agent - 工具使用 | 69.40Thinking Enabled | Tools | 74.20Thinking Enabled | Tools |
OSWorld-Verified AI Agent - 工具使用 | 73.10Thinking Enabled | Tools | 70.00Thinking Enabled | Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 53.56Thinking Enabled | 66.00Thinking Enabled | Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Kimi K2.6Moonshot AI | MiniMax M3MiniMaxAI |
|---|---|---|
Core specsRelease | 2026-04-20 | 2026-06-01 |
Context length | 256K | 1M |
Parameters | 1T | 428B |
Active parameters | 32B | 23B |
Max output | Not provided | 524288 |
MoE | Yes | Yes |
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 | Open Source · MIT License |
Weights Open Source | Open Source · Modified MIT | Open Source · MiniMax-Modified MIT |
Commercial use | 免费商用授权 | 不可以商用 |
Local deploymentWeights | Not provided | Hugging Face |
Source repo | Not provided | GitHub |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
Video Input/Output | / | / |
ResourcesPaper / report | Kimi K2.6: Advancing Open-Source Coding | MiniMax M3: Coding & Agentic Frontier with MSA Architecture, 1M Context and Native Multimodality |

MiniMax M3
MiniMaxAI