Model Comparison

Kimi K2.5 vs MiniCPM-SALA

Kimi K2.5 significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

Kimi K2.5 outperforms in 3 benchmarks (AIME 2025, LiveCodeBench v6, MMLU-Pro), while MiniCPM-SALA is better at 0 benchmarks.

Kimi K2.5 significantly outperforms across most benchmarks.

Tue Apr 14 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Tue Apr 14 2026 • llm-stats.com
Moonshot AI
Kimi K2.5
Input tokens$0.60
Output tokens$2.50
Best providerFireworks
OpenBMB
MiniCPM-SALA
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

990.5B diff

Kimi K2.5 has 990.5B more parameters than MiniCPM-SALA, making it 10451.6% larger.

Moonshot AI
Kimi K2.5
1000.0Bparameters
OpenBMB
MiniCPM-SALA
9.5Bparameters
1000.0B
Kimi K2.5
9.5B
MiniCPM-SALA

Context Window

Maximum input and output token capacity

Only Kimi K2.5 specifies input context (262,100 tokens). Only Kimi K2.5 specifies output context (262,100 tokens).

Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
OpenBMB
MiniCPM-SALA
Input- tokens
Output- tokens
Tue Apr 14 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Kimi K2.5 supports multimodal inputs, whereas MiniCPM-SALA does not.

Kimi K2.5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Kimi K2.5

Text
Images
Audio
Video

MiniCPM-SALA

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while MiniCPM-SALA uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

Kimi K2.5

MIT

Open weights

MiniCPM-SALA

Apache 2.0

Open weights

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while MiniCPM-SALA was released on 2026-02-11.

MiniCPM-SALA is 1 month newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

2 months ago

MiniCPM-SALA

Feb 11, 2026

2 months ago

2w newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Moonshot AI
Larger context window (262,100 tokens)
Supports multimodal inputs
Higher AIME 2025 score (96.1% vs 78.3%)
Higher LiveCodeBench v6 score (85.0% vs 52.0%)
Higher MMLU-Pro score (87.1% vs 67.0%)
OpenBMB

Detailed Comparison

AI Model Comparison Table
Feature
Moonshot AI
Kimi K2.5
OpenBMB
MiniCPM-SALA

FAQ

Common questions about Kimi K2.5 vs MiniCPM-SALA

Kimi K2.5 significantly outperforms across most benchmarks. Kimi K2.5 is made by Moonshot AI and MiniCPM-SALA is made by OpenBMB. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%. MiniCPM-SALA scores HumanEval: 95.1%, RULER 64k: 92.7%, RULER 128k: 89.4%, MBPP: 89.1%, RULER 512K: 87.1%.
Kimi K2.5 supports 262K tokens and MiniCPM-SALA supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include multimodal support (yes vs no), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.
Kimi K2.5 is developed by Moonshot AI and MiniCPM-SALA is developed by OpenBMB.