Weekly rankings
Every published week of the LLM1 overall leaderboard. Scores are weighted averages of independent benchmark results — see the methodology.
Week of Oct 3, 2026Latest
| Rank | Model | Provider | Score | Change |
|---|---|---|---|---|
| 1 | Muse Spark 1.3 | Meta | 83.2 | — |
| 2 | Claude Sonnet 5.5 | Anthropic | 81.9 | — |
| 3 | Gemini 4 Argon | Google DeepMind | 81.9 | — |
| 4 | Claude Fable 5.1 | Anthropic | 81.7 | — |
| 5 | Gemini 3.8 Flash | Google DeepMind | 81.7 | — |
| 6 | Claude Opus 5.5 | Anthropic | 78.7 | — |
| 7 | GPT-6 Astra | OpenAI | 78.4 | — |
| 8 | GLM-5.3 | z.ai | 76.4 | — |
| 9 | Qwen3.8 Max | Alibaba Qwen | 75.5 | — |
| 10 | DeepSeek V4.1 Flash | DeepSeek | 74.1 | — |
| 11 | Kimi K3 | Moonshot AI | 72.4 | — |
| 12 | MiMo-V2.6-Pro | Xiaomi | 71.7 | — |
| 13 | GPT-6.1 Sol | OpenAI | 71.4 | — |
| 14 | GPT-6 Luna | OpenAI | 70.2 | — |
| 15 | DeepSeek V4 Pro | DeepSeek | 68.5 | — |
| 16 | Grok 4.7 | xAI | 67.8 | — |
| 17 | Step 5 Preview | StepFun | 67.2 | — |
| 18 | MiniMax-M3 | MiniMax | 59.6 | — |
| 19 | Qwen3.8 27B | Alibaba Qwen | 52.3 | — |
| 20 | K2 Horizon MoVA 36B A4B | Institute of Foundation Models | 43.1 | — |
| 21 | Mistral Medium 3.5 | Mistral AI | 42.3 | — |
| 22 | Gemma 4 26B A4B | Google DeepMind | 41.1 | — |
| 23 | Muse Glimmer | Meta | 39.0 | — |
| 24 | Qwen3.6 35B A3B | Alibaba Qwen | 38.2 | — |
| 25 | K2 Horizon 7B | Institute of Foundation Models | 36.2 | — |
| 26 | Granite 4.2 30B | IBM | 34.8 | — |