Best Open-Source AI Models (2026)
The strongest models with openly downloadable weights — from DeepSeek, Qwen, GLM (Z.ai), Llama, Mistral and others — ranked by RunFree Score. These you can self-host, fine-tune or run privately.
| # | Model | RunFree Score | Price / 1M |
|---|---|---|---|
| 1 | Qwen3 Max Thinking | 94.8 | $1.56 |
| 2 |  GLM 5.2 | 86.3 | $1.46 |
| 3 |  DeepSeek V4 Pro | 72.4 | $0.54 |
| 4 | DeepSeek V4 Flash | 59.1 | $0.11 |
| 5 |  Kimi K2 Thinking | 45.2 | $1.07 |
| 6 |  Llama 4 Maverick | 0 | $0.26 |
Based on verified public benchmarks; see methodology. Prices are blended 3:1 input:output per million tokens.
More rankings
FAQ
What is the best open-source ai models?
Qwen3 Max Thinking leads this ranking with 94.8. The full top 20 is in the table above, updated as new benchmark results land.
How is this ranking calculated?
The strongest models with openly downloadable weights — from DeepSeek, Qwen, GLM (Z.ai), Llama, Mistral and others — ranked by RunFree Score. These you can self-host, fine-tune or run privately. We only use publicly verifiable benchmark results with cited sources — no estimates. See our methodology page for the exact formula.
How often does this list change?
Pricing and model availability refresh hourly from OpenRouter; benchmark scores update whenever a lab publishes new official results. The ranking reflects the latest verified data.