~ / best / open-source-coding-models

Best Open Source Coding Models for Agents

Open models pair well with open-source agents when you need cost control, portability, or local deployment options.

#ModelDeepSWEContextCostOpen
1DeepSeek V4.1 Flash
DeepSeek
74.2not listed$0.15/$0.60Yes
2MiMo-V2.6-Pro
Xiaomi
71.91M$0.435/$0.87Yes
3Kimi K3
Moonshot AI
69.01M$3/$15Yes
4MiMo-V2.6-Flash
Xiaomi
67.91M$0.14/$0.28Yes
5GLM-5.3
Z.ai
66.9not listednot listedYes
6GLM-5.3-Flash
Z.ai
63.4not listednot listedYes
7DeepSeek V4 Pro 0813
DeepSeek
62.81M$0.435/$0.87Yes
8Qwen3.8-Flash-Next
Alibaba
58.7not listednot listedYes
9Qwen3.8 Max
Alibaba
56.61M$2/$6Yes
10GLM-5.2
Z.ai
44.01M$0.95/$3Yes
11Qwen3.8-27B
Alibaba
42.2262Knot listedYes
12Laguna S 2.1
Poolside
40.41Mnot listedYes
13Kimi K2.7 Code
Moonshot AI
31.0not listednot listedYes
How to read this: Agent pages score the wrapper and workflow. Stack pages score agent plus model combinations.

Related rankings

Other useful paths through the dataset.

Best CLI AI Coding Agents

Terminal-first coding agents are best when you want repo-level edits, scriptable workflows, and less IDE lock-in.

13 entries

Best Open Source AI Coding Agents

Open-source agents are strongest when you want provider choice, local-model support, and transparent agent behavior.

13 entries

Best AI Coding Agents for VS Code

IDE-focused agents are best for daily coding, codebase navigation, completions, and fast multi-file edits.

13 entries

Best Browser AI Coding Agents

Browser coding agents are useful when you want to build, preview, and ship without managing a local development environment.

13 entries