This is the dedicated landing page for high-intent queries like “llm leaderboard”, “ai ranking”, and “ai rankings”, with emphasis on current order, top-model separation, and recent real movement.
| # | Model | Provider | Score | 7d move | Input price |
|---|---|---|---|---|---|
| #1 | GPT-5.4 Pro | OpenAI | 94 | +3 | $30.00/M |
| #2 | GPT-5.4 | OpenAI | 94 | +3 | $2.50/M |
| #3 | GPT-5.2 Pro | OpenAI | 93 | +16 | $21.00/M |
| #4 | GPT-5.2 | OpenAI | 93 | +16 | $1.75/M |
| #5 | Claude Opus 4.6 | Anthropic | 92 | +2 | $5.00/M |
| #6 | GPT-5 Pro | OpenAI | 92 | +24 | $15.00/M |
| #7 | o3 Deep Research | OpenAI | 92 | +30 | $10.00/M |
| #8 | Claude Opus 4.5 | Anthropic | 90 | +21 | $5.00/M |
| #9 | GPT-5 | OpenAI | 90 | +34 | $1.25/M |
| #10 | Gemini 3 Flash Preview | 89 | +12 | $0.500/M | |
| #11 | Claude Sonnet 4.6 | Anthropic | 89 | -5 | $3.00/M |
| #12 | Claude Sonnet 4.5 | Anthropic | 89 | +6 | $3.00/M |
| #13 | o3 Pro | OpenAI | 87 | +55 | $20.00/M |
| #14 | Grok 4.1 Fast | xAI | 87 | -12 | $0.200/M |
| #15 | GPT-5.4 Nano | OpenAI | 87 | -6 | $0.200/M |
| #16 | GPT-5.4 Mini | OpenAI | 87 | -6 | $0.750/M |
| #17 | Grok 4.20 Beta | xAI | 86 | -16 | $2.00/M |
| #18 | Grok 4 | xAI | 86 | +41 | $3.00/M |
| #19 | Gemini 3.1 Pro Preview | 86 | -4 | $2.00/M | |
| #20 | o3 | OpenAI | 85 | +59 | $2.00/M |
| #21 | GPT-5.1 | OpenAI | 85 | +2 | $1.25/M |
| #22 | MiMo-V2-Omni | Xiaomi | 85 | +4 | $0.400/M |
| #23 | MiMo-V2-Pro | Xiaomi | 85 | +1 | $1.00/M |
| #24 | Seed-2.0-Lite | ByteDance | 85 | +3 | $0.250/M |
| #25 | Qwen3.5-9B | Alibaba | 85 | +10 | $0.050/M |
This page ranks live coding and language models using LM Market Cap composite scores, which combine capabilities, pricing, context, output capacity, versatility, and recency into a single leaderboard surface.
The models directory is for browsing the full catalog across providers and categories. This page is the competitive LLM ranking page aimed at users who want the top-performing models in rank order.
Yes. The linked rank-change and trends surfaces now compare live rankings against the latest archived weekly snapshot rather than synthetic movement estimates.