MiniMax-M2.5
MiniMaxMiniMaxOpen WeightMIT · Commercial OK
Description
MiniMax M2.5 is the world's first production-level model designed natively for Agent scenarios. Building on the M2.1 foundation, M2.5 delivers significant improvements in programming, tool calling, search, and office productivity. With only 10B activation parameters from its 230B MoE architecture, it achieves competitive performance against top international models like Claude Opus 4.6 while maintaining high throughput and efficient inference. M2.5 supports full-stack development for PC, App, and cross-platform applications, and excels in agentic workflows including automated customer support, data-analysis pipelines, and complex task execution.
Release Date
2026-02-12
Parameters
230.0B
Context Length
197K
Modalities
image, text
Capability Radar
37
general
38
coding
85
reasoning
57
scienceest.
70
agents
60
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agents & Tools | 27 | 65.0 | LS |
| Code Ranking | 68 | 68.0 | AA |
| General Ranking | 46 | 79.0 | AA |
| Science | 71 | 67.0 | AA |
Benchmark Scores (LLM Stats)
Agents
BrowseComp
76.3%SR
MEWC
74.4%SR
SWE-Bench Pro
55.4%SR
VIBE-Pro
54.2%SR
Code
SWE-Bench Verified
80.2%SR
Multi-SWE-Bench
51.3%SR
Finance
GDPval-MM
59.0%SR
General
BFCL_v3_MultiTurn
76.8%SR
AA Evaluation Indices
Intelligence Index41.9
Coding Index37.4
Tau21.0
Gpqa0.8
Ifbench0.7
Lcr0.7
Scicode0.4
Terminalbench Hard0.3
Hle0.2
LLM Stats Category Scores
Frontend Development80
Search80
Agents70
Code60
Finance60
General60
Multimodal60
Reasoning60
Pricing
Input Price$0.3 / 1M tokens
Output Price$1.2 / 1M tokens
Blended Price (3:1)$0.525 / 1M tokens
Speed
Tokens/sec84.0 tokens/s
Time to First Token1.44s
Time to Answer25.25s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| MiniMax | 300K | 1.2M |