Model Comparison

Kimi K2.5 vs North Mini Code 1.0Which is better in 2026?

Kimi K2.5 significantly outperforms across most benchmarks.

Verdict: Kimi K2.5 vs North Mini Code 1.0 — which is better?

Kimi K2.5 (by Moonshot AI) and North Mini Code 1.0 (by Cohere) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Kimi K2.5 outperforms in 5 benchmarks (LiveCodeBench v6, SciCode, SWE-Bench Pro, SWE-Bench Verified, Terminal-Bench 2.0), while North Mini Code 1.0 is better at 0 benchmarks. Kimi K2.5 significantly outperforms across most benchmarks.

Choose Kimi K2.5 if…

  • you want the strongest raw capability — it leads on 5 of 5 shared benchmarks

Choose North Mini Code 1.0 if…

  • you want the most recent training data — it shipped Jun 2026

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Kimi K2.5 outperforms in 5 benchmarks (LiveCodeBench v6, SciCode, SWE-Bench Pro, SWE-Bench Verified, Terminal-Bench 2.0), while North Mini Code 1.0 is better at 0 benchmarks.

Kimi K2.5 significantly outperforms across most benchmarks.

Tue Jul 28 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

970.0B diff

Kimi K2.5 has 970.0B more parameters than North Mini Code 1.0, making it 3233.3% larger.

Moonshot AI
Kimi K2.5
1.0Tparameters
Cohere
North Mini Code 1.0
30.0Bparameters
1000.0B
Kimi K2.5
30.0B
North Mini Code 1.0

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
Cohere
North Mini Code 1.0
Input- tokens
Output- tokens
Tue Jul 28 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Kimi K2.5 supports multimodal inputs, whereas North Mini Code 1.0 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

North Mini Code 1.0

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while North Mini Code 1.0 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

North Mini Code 1.0

Apache 2.0

Open weights

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while North Mini Code 1.0 was released on 2026-06-09.

North Mini Code 1.0 is 4 months newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

6 months ago

North Mini Code 1.0

Jun 9, 2026

1 months ago

4mo 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 LiveCodeBench v6 score (85.0% vs 70.3%)
Higher SciCode score (48.7% vs 38.2%)
Higher SWE-Bench Pro score (50.7% vs 40.2%)
Higher SWE-Bench Verified score (76.8% vs 67.6%)
Higher Terminal-Bench 2.0 score (50.8% vs 36.0%)
Cohere

No standout differentiators in the data we have for this pair.

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Kimi K2.5 and North Mini Code 1.0 side-by-side, then vote on the output you prefer.

Kimi K2.5
✓ Preferred
North Mini Code 1.0
Open in Playground
AI Model Comparison Table
Feature
Moonshot AI
Kimi K2.5
Cohere
North Mini Code 1.0

FAQ

Common questions about Kimi K2.5 vs North Mini Code 1.0.

Which is better, Kimi K2.5 or North Mini Code 1.0?

Kimi K2.5 significantly outperforms across most benchmarks. Kimi K2.5 is made by Moonshot AI and North Mini Code 1.0 is made by Cohere. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Kimi K2.5 compare to North Mini Code 1.0 in benchmarks?

Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%. North Mini Code 1.0 scores LiveCodeBench v6: 70.3%, SWE-Bench Verified: 67.6%, SWE-Bench Pro: 40.2%, SciCode: 38.2%, Terminal-Bench 2.0: 36.0%.

What are the context window sizes for Kimi K2.5 and North Mini Code 1.0?

Kimi K2.5 supports 262K tokens and North Mini Code 1.0 supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Kimi K2.5 and North Mini Code 1.0?

Key differences include multimodal support (yes vs no), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2.5 and North Mini Code 1.0?

Kimi K2.5 is developed by Moonshot AI and North Mini Code 1.0 is developed by Cohere.

Related comparisons