Kimi

Your AI assistant for everyday use

5.0•10 reviews•

2.5K followers

Your AI assistant for everyday use

5.0•10 reviews•

2.5K followers

•

•

- Real-time web search across 100+ websites - Analyze up to 50 files (PDFs, Docs, PPTs, Images) with ease - AI slides & websites maker - State of the art coding capabilities - Enhanced image understanding beyond basic text extraction

Kimi Reviews

The community submitted 10 reviews to tell us what they like about Kimi, what Kimi can do better, and more.

5.0

Based on 10 reviews

Review Kimi?

Reviewers mostly see Kimi as a strong coding model with unusually good price-to-performance. A user says K2.7 follows complex instructions well, writes cleaner code, and gives strong GitHub PR reviews that catch meaningful issues and understand context, especially inside agent-style workflows. The main weakness is consistency over long-running tasks and a remaining gap versus top proprietary models when starting brand-new projects. Founders of Edgee and Oxlo.ai echo the coding strength, while the makers of CraftBot use it as their default model.

Summarized with AI

Wispr Flow: Dictation That Works EverywhereStop typing. Start speaking. 4x faster.

Promoted

Reviews

All Reviews

Most Informative

Founder Reviews (9)

Other Reviews (1)

•7 reviews

What's great

code generation (1)review management (1)

I've been using both K2.6 and K2.7 for software engineering over the past few weeks, primarily through OpenCode.

K2.7 is a noticeable improvement for coding. It follows complex instructions better, produces cleaner code, and feels more reliable during agentic development workflows.

One area where it really impressed me was GitHub pull request code reviews. I tested it on a core TypeScript project, and the review quality was genuinely strong. It caught meaningful issues, provided useful suggestions, and understood the broader context of the changes instead of focusing only on superficial style comments.

The OpenCode integration is also excellent. The overall experience feels smooth and natural, making it easy to use K2 as part of a real development workflow.

When starting an entirely new project from scratch, I still think Claude Opus 4.8 has an advantage. However, for an open-source model, K2.7 exceeded my expectations by a wide margin. It's one of the most capable open models I've used, and I'll definitely keep using it.

What needs improvement

code agent gets stuck (1)

The model is already impressive, especially considering it's open source. The biggest opportunity is continuing to improve long-running agent consistency and narrowing the remaining gap with frontier proprietary models when building entirely new projects from scratch. If that trajectory continues, K2 has the potential to become one of the default choices for software engineering.

vs Alternatives

I regularly use Claude Code Opus and codex-gpt-5.5-high for complex engineering work and also evaluate other open models such as GLM-5.2, qwen-code-next.

I wanted to see how K2.7 would perform in real-world development rather than synthetic benchmarks. After using it with OpenCode and testing it for GitHub PR reviews, it proved to be a practical and capable model that fits naturally into my daily workflow.

Ratings

Ease of use

Reliability

Value for money

Customization

Report

101 views2mo ago

Kimi

Your AI assistant for everyday use

Your AI assistant for everyday use

Kimi Reviews

The community submitted 10 reviews to tell us what they like about Kimi, what Kimi can do better, and more.

What's great

What needs improvement

vs Alternatives

Alternatives Considered

Alternatives Considered

Alternatives Considered