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。
MiniMax M2.5
MiniMaxAI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: none clear / Relative gap: 综合评估 -9.9
Relative edge: 综合评估 +9.9 / 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
MiniMax M3 · 70.84
Best single
MiniMax M3 · BrowseComp 83.50
Modality coverage
MiniMax M3 · 3 modalities
Head to head
3
Benchmarks
0
Wins
3
Losses
-6.89
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 | MiniMax M2.5 | MiniMax M3 |
|---|---|---|
LiveBench 综合评估 | 60.14Deep Thinking Mode | 70.02Deep Thinking Mode |
SWE-Bench Pro - Public 编程与软件工程 | 55.40Thinking Enabled ｜ Tools | 59.00Thinking Enabled ｜ Tools |
BrowseComp AI Agent - 信息收集 | 76.30Thinking Enabled ｜ Tools | 83.50Thinking Enabled ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | MiniMax M2.5MiniMaxAI | MiniMax M3MiniMaxAI |
|---|---|---|
Core specsRelease | 2026-02-12 | 2026-06-01 |
Context length | 128K | 1M |
Parameters | 229B | 428B |
Active parameters | 10B | 23B |
Max output | Not provided | 524288 |
MoE | Yes | Yes |
LicenseCode Open Source | Open Source · MIT License | Open Source · MIT License |
Weights Open Source | Open Source · MINIMAX MODEL LICENSE | Open Source · MiniMax-Modified MIT |
Commercial use | 免费商用授权 | 不可以商用 |
Local deploymentWeight size | 230GB | Not provided |
VRAM for weights | ≈ 230 GB (weights only, excludes KV cache) | Not provided |
Weights | Hugging Face | Hugging Face |
Source repo | GitHub | GitHub |
Modality supportText Input/Output | / | / |
Image Input/Output | Not provided | / |
Video Input/Output | Not provided | / |
ResourcesPaper / report | MiniMax M2.5: Built for Real-World Productivity. | MiniMax M3: Coding & Agentic Frontier with MSA Architecture, 1M Context and Native Multimodality |
MiniMax M3
MiniMaxAI
