Open-weight models (Llama, Qwen, DeepSeek, Mistral…) ranked side by side with the proprietary frontier (GPT, Claude, Gemini, Grok) — live pricing, context, benchmarks and capabilities. No marketing — just the facts.
| # | Model | Creator | Intelligence | Coding |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (Max, Default Fallback) | Anthropic | 57.6 | — |
| 2 | Claude Sonnet 5.5 (Max, Default Fallback) | Anthropic | 56.0 | — |
| 3 | Claude Fable 5.1 (Max, Default Fallback) | Anthropic | 53.4 | 81.6 |
| 4 | GPT-6 Astra (Max) | OpenAI | 52.7 | 76.9 |
| 5 | Gemini 4 Argon (High) | 52.6 | — | |
| 6 | GPT-6.1 Sol (Max) | OpenAI | 51.8 | — |
| 7 | Claude Opus 5 (Max) | Anthropic | 50.8 | 78.0 |
| 8 | Claude Fable 5 (Max, Opus 4.8 Fallback) | Anthropic | 49.6 | 76.5 |
| 9 | Muse Spark 1.3 (Max) | Meta | 48.1 | 75.8 |
| 10 | GPT-6 Sol (Max) | OpenAI | 47.6 | — |
| 11 | GPT-5.6 Sol (Max) | OpenAI | 47.0 | 77.4 |
| 12 | Grok 4.7 (Xhigh) | SpaceXAI | 46.4 | — |
| 13 | MiMo-V2.6-Pro | Xiaomi | 46.3 | — |
| 14 | Qwen3.8 Max (0902) | Alibaba | 45.4 | 76.2 |
| 15 | GLM-5.3 (Max) | Z AI | 44.8 | 74.8 |
| 16 | Grok 4.6 (High) | SpaceXAI | 44.3 | 76.8 |
| 17 | Step 5 Preview | StepFun | 43.7 | — |
| 18 | Kimi K3 (Max) | Kimi | 43.6 | 76.2 |
| 19 | GPT-5.6 Terra (Max) | OpenAI | 42.1 | 76.7 |
| 20 | Claude Opus 4.8 (Max) | Anthropic | 41.8 | 74.3 |
| 21 | GLM 5.3 Flash | Z AI | 41.8 | 71.5 |
| 22 | Ling 3.1 Flash | InclusionAI | 41.1 | — |
| 23 | Gemini 3.8 Flash (High) | 40.9 | 76.3 | |
| 24 | Claude Opus 4.7 (Max) | Anthropic | 40.7 | 73.6 |
| 25 | Qwen3.8 2.4T A95B | Alibaba | 39.9 | 71.9 |
| 26 | Qwen3.8-Flash-Next | Alibaba | 39.8 | 73.1 |
| 27 | Gemini 3.7 Flash (Medium) | 39.6 | 71.5 | |
| 28 | Muse Spark 1.2 (Xhigh) | Meta | 39.6 | 72.2 |
| 29 | DeepSeek V4.1 Flash (Max) | DeepSeek | 39.5 | — |
| 30 | GPT-5.4 (Xhigh) | OpenAI | 39.0 | 71.1 |
| 31 | Grok 4.5 (High) | SpaceXAI | 38.8 | 72.4 |
| 32 | GPT-5.5 (Xhigh) | OpenAI | 38.4 | 74.9 |
| 33 | Claude Sonnet 5 (Max) | Anthropic | 38.2 | 71.5 |
| 34 | GPT-6 Luna (Max) | OpenAI | 38.1 | — |
| 35 | MiMo-V2.6-Flash | Xiaomi | 37.9 | — |
| 36 | GPT-5.6 Luna (Max) | OpenAI | 37.3 | 71.4 |
| 37 | DeepSeek V4 Pro 0813 (Max) | DeepSeek | 36.0 | 68.8 |
| 38 | DeepSeek V4 Flash Vision (Max) | DeepSeek | 34.8 | 65.0 |
| 39 | DeepSeek V4 Flash 0731 (Max) | DeepSeek | 34.3 | 69.1 |
| 40 | Gemini 3.6 Flash (High) | 34.0 | 69.2 | |
| 41 | JT-4.1 Flash 236B A21B (Reasoning) | China Mobile | 33.9 | — |
| 42 | GLM-5.2 (Max) | Z AI | 33.7 | 68.8 |
| 43 | Muse Spark 1.1 (Xhigh) | Meta | 33.7 | 71.3 |
| 44 | Qwen3.8 27B (Xhigh) | Alibaba | 33.7 | 68.1 |
| 45 | Gemini 3.5 Flash (Medium) | 33.6 | — | |
| 46 | Motif 3 | Motif Technologies | 33.6 | 63.5 |
| 47 | GPT-5.3 Codex (Xhigh) | OpenAI | 32.5 | — |
| 48 | Claude Opus 4.6 (Max) | Anthropic | 31.9 | — |
| 49 | Muse Spark | Meta | 31.3 | 58.6 |
| 50 | K2 Horizon 375B A23B | Institute of Foundation Models | 30.5 | 61.5 |
| 51 | DeepSeek V4 Pro 0424 (Max) | DeepSeek | 30.4 | 59.4 |
| 52 | GPT-5.2 (Xhigh) | OpenAI | 30.4 | — |
| 53 | Claude Sonnet 4.6 (Max) | Anthropic | 30.1 | 63.0 |
| 54 | Gemini 3.1 Pro Preview | 29.7 | 68.8 | |
| 55 | Qwen3.7 Max | Alibaba | 29.5 | 66.0 |
| 56 | MiniMax-M3 | MiniMax | 29.2 | 58.6 |
| 57 | Claude Opus 4.5 (Reasoning) | Anthropic | 29.1 | — |
| 58 | MiMo-V2-Pro | Xiaomi | 28.6 | — |
| 59 | GPT-5.2 Codex (Xhigh) | OpenAI | 28.5 | — |
| 60 | Qwen3.6 Max Preview | Alibaba | 28.4 | — |
How this is ranked: models are ordered by real usage popularity (weekly tokens processed across apps), via the OpenRouter API. Only open-weight models are included (Llama, DeepSeek, Qwen, Mistral, Gemma, Kimi, GLM, Phi, Nemotron, and more). Pricing is per million tokens; context is the maximum window. Movement arrows compare today's rank to the previous snapshot. Data refreshes daily.