Xiaomi
MiMo-V2.5-Pro
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution
xiaomi/mimo-v2.5-pro
Context
1M
Output
131.1K
Released
2026-04-22
Knowledge cutoff
2024-12
Types
InputText
OutputText
Reasoning
Supported
Tool use
Supported
Structured output
—
Attachments
—
Open weights
Supported
Provider pricing
Vercel AI Gateway
InText
OutText
- Price
- $0.30 / $0.61
- Context
- 1.1M
- Status
- Stable
Kilo Gateway
InText
OutText
- Price
- $0.44 / $0.87
- Context
- 1M
- Status
- Stable
NanoGPT
InText
OutText
- Price
- $0.44 / $0.87
- Context
- 1M
- Status
- Stable
OpenRouter
InText
OutText
- Price
- $0.44 / $0.87
- Context
- 1.1M
- Status
- Stable
CrossModel
InText
OutText
- Price
- $0.47 / $0.94
- Context
- 1M
- Status
- Stable
AI/ML API
InText
OutText
- Price
- $0.60 / $1.20
- Context
- 1M
- Status
- Stable
ZenMux
InText
OutText
- Price
- $1.00 / $3.00
- Context
- 1M
- Status
- Stable
Benchmarks
SWE-Bench Verified
78.9 · resolved
SWE-Bench Pro
57.2 · resolve rate
GPQA Diamond
86.6 · accuracy
DeepSWE
19 · score
ProgramBench
12.5 · score
MiMo Code Bench
40.4 · score
AutomationBench
16 · score
Toolathlon-Verified
49.1 · score
GDPval-AA
1107 · Elo
Agents' Last Exam
13.2 · score
Terminal-Bench
1.5 · score
Terminal-Bench
65.2 · score
JobBench
25 · score
CyberGym
40 · score
MiMo Cyber Bench
0 · score
ExploitGym
0.2 · score
ExploitBench
16.6 · score
SEC-Bench Pro
17.7 · score