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 K3
Moonshot AI
MiniMax M3
MiniMaxAI
Best overall
Kimi K3 · 88.10
Best single
Kimi K3 · BrowseComp 91.20
Modality coverage
Kimi K3 · 3 modalities
Head to head
3
Benchmarks
3
Wins
0
Losses
+14.93
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.
3 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Kimi K3 | MiniMax M3 |
|---|---|---|
BrowseComp AI Agent - 信息收集 | 91.20Thinking Level · High ｜ Tools | 83.50Thinking Enabled ｜ Tools |
OSWorld-Verified AI Agent - 工具使用 | 84.80Thinking Level · High ｜ Tools | 70.00Thinking Enabled ｜ Tools |
TerminalBench 2.1 AI Agent - 工具使用 | 88.30Thinking Level · High ｜ Tools | 66.00Thinking Enabled ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Kimi K3Moonshot AI | MiniMax M3MiniMaxAI |
|---|---|---|
Core specsRelease | 2026-07-16 | 2026-06-01 |
Context length | 1M | 1M |
Parameters | 28000 | 4280 |
Active parameters | 1040 | 230 |
Max output | 1048576 | 524288 |
MoE | Yes | Yes |
LicenseCode Open Source | Not provided | Closed Source |
Weights Open Source | Not provided | Not provided |
Commercial use | 有条件免费商用授权 | 不可以商用 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
Video Input/Output | / | / |
ResourcesPaper / report | Kimi K3 技术报告 | MiniMax M3: Coding & Agentic Frontier with MSA Architecture, 1M Context and Native Multimodality |
