293 models ranked for open source development. Scored with bonuses for open source licenses (+10), free access (+5), large context (full codebases), large output (complete components), reasoning, and streaming.
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 ProOpenAI | 91 |
| 2 | GPT-5.2 ProOpenAI | 90 |
| 3 | GPT-5 ProOpenAI | 90 |
| 4 | Qwen3 VL 30B A3B ThinkingAlibaba | 69 |
| 5 | Qwen3 VL 235B A22B ThinkingAlibaba | 69 |
| 6 | o3 ProOpenAI | 82 |
| 7 | Claude Opus 4.1Anthropic | 81 |
| 8 | Nemotron Nano 12B 2 VL (free)NVIDIA | 64 |
| 9 | Gemini 3.1 Pro Preview Custom ToolsGoogle | 68 |
| 10 | o1-proOpenAI | 77 |
| 11 | Claude Opus 4Anthropic | 76 |
| 12 | o3 Deep ResearchOpenAI | 74 |
| 13 | Step 3.5 Flash (free)StepFun | 58 |
| 14 | Qwen3.5-FlashAlibaba | 62 |
| 15 | gpt-oss-120b (free)OpenAI | 56 |
| 16 | gpt-oss-20b (free)OpenAI | 56 |
| 17 | Qwen3.5-122B-A10BAlibaba | 61 |
| 18 | Qwen3.5 397B A17BAlibaba | 61 |
| 19 | Qwen3.5-35B-A3BAlibaba | 61 |
| 20 | Qwen3.5-27BAlibaba | 61 |
| 21 | Claude Opus 4.6Anthropic | 71 |
| 22 | Claude Opus 4.5Anthropic | 70 |
| 23 | GPT-5.4OpenAI | 70 |
| 24 | Kimi K2.5Moonshot AI | 59 |
| 25 | Claude Sonnet 4.5Anthropic | 69 |
| 26 | Qwen3 235B A22B Thinking 2507Alibaba | 57 |
| 27 | GPT-5.2OpenAI | 68 |
| 28 | Gemini 3.1 Pro PreviewGoogle | 68 |
| 29 | Gemini 3 Pro PreviewGoogle | 68 |
| 30 | Claude Sonnet 4.6Anthropic | 68 |
Open source models come with publicly available code and weights. You can inspect the model architecture, training approach, and data usage. This transparency builds trust and enables community-driven improvements and customizations.
Contribute directly to open source AI projects. Fix bugs, improve performance, add features, and participate in discussions. Open source models benefit from collective intelligence and diverse perspectives across the developer community.
Deploy open source models on your own infrastructure. No vendor lock-in, no monthly subscriptions, complete data privacy. Run models locally on your laptop, server, or cloud infrastructure with full control over updates and deployments.
Fine-tune open source models on your domain-specific data. Adapt models for specialized tasks, proprietary knowledge, or unique vocabularies. Open source enables experimentation without restrictions or vendor approval.