Inkling-Small vs MiMo-V2.5-Pro
Both models are evenly matched across the benchmarks. Inkling-Small is 1.0x cheaper per token.
Thinking Machines Lab · Xiaomi · Updated for 2026
Which is better?
Inkling-Small outperforms in 2 benchmarks (GPQA, SWE-Bench Verified), while MiMo-V2.5-Pro is better at 2 benchmarks (Humanity's Last Exam, SWE-Bench Pro). Both models are evenly matched across the benchmarks.
MiMo-V2.5-Pro also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.
Based on current benchmark, pricing, and model metadata for 2026.
Choose Inkling-Small
- you want the most recent training data — it shipped Jul 2026
Choose MiMo-V2.5-Pro
- you process long inputs — it offers a 1,048,576 token context window
At a glance
The differences that matter most.
Performance Benchmarks
Comparative analysis across standard metrics
Inkling-Small outperforms in 2 benchmarks (GPQA, SWE-Bench Verified), while MiMo-V2.5-Pro is better at 2 benchmarks (Humanity's Last Exam, SWE-Bench Pro).
Both models are evenly matched across the benchmarks.
Arena Performance
Playground indexes and blind preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Inkling-Small ($0.30/1M tokens) is 1.4x cheaper than MiMo-V2.5-Pro ($0.43/1M tokens).
For output processing, Inkling-Small ($1.20/1M tokens) is 1.4x more expensive than MiMo-V2.5-Pro ($0.87/1M tokens).
In conclusion, MiMo-V2.5-Pro is more expensive than Inkling-Small.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
MiMo-V2.5-Pro has 747.2B more parameters than Inkling-Small, making it 270.7% larger.
Context Window
Maximum input and output token capacity
MiMo-V2.5-Pro accepts 1,048,576 input tokens compared to Inkling-Small's 256,000 tokens. Inkling-Small can generate longer responses up to 256,000 tokens, while MiMo-V2.5-Pro is limited to 131,072 tokens.
Input Capabilities
Supported data types and modalities
Inkling-Small supports multimodal inputs, whereas MiMo-V2.5-Pro does not.
Inkling-Small can handle both text and other forms of data like images, making it suitable for multimodal applications.
Inkling-Small
MiMo-V2.5-Pro
License
Usage and distribution terms
Inkling-Small is licensed under Apache 2.0, while MiMo-V2.5-Pro uses MIT.
License differences may affect how you can use these models in commercial or open-source projects.
Apache 2.0
Open weights
MIT
Open weights
Release Timeline
When each model was launched
Inkling-Small was released on 2026-07-30, while MiMo-V2.5-Pro was released on 2026-04-27.
Inkling-Small is 3 months newer than MiMo-V2.5-Pro.
Jul 30, 2026
3 weeks ago
3mo newerApr 27, 2026
4 months ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Inkling-Small is available from Thinking Machines Lab. MiMo-V2.5-Pro is available from Xiaomi, DeepInfra, Novita.
Inkling-Small
MiMo-V2.5-Pro
Outputs Comparison
Judge for yourself.
Run your own prompts against Inkling-Small and MiMo-V2.5-Pro side-by-side, then vote on the output you prefer.
FAQ
Common questions about Inkling-Small vs MiMo-V2.5-Pro.