Rankings
Updated: February 2026
LLM Rankings
| # | Model | Company | Arena ELO | Coding | Reasoning | Trend |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 4.6 | Anthropic | 1385 | 96.8% | 95.2% | + |
| 2 | GPT-5 | OpenAI | 1372 | 96.1% | 94.5% | - |
| 3 | Gemini 2.5 Pro | 1358 | 95.2% | 94% | + | |
| 4 | GPT-5 Turbo | OpenAI | 1345 | 94.5% | 93.1% | NEW |
| 5 | Claude Sonnet 4.5 | Anthropic | 1338 | 93.8% | 92.4% | - |
| 6 | DeepSeek R1 | DeepSeek | 1330 | 93.5% | 93.8% | NEW |
| 7 | DeepSeek V3 | DeepSeek | 1322 | 92.8% | 91.9% | + |
| 8 | Llama 4 405B | Meta | 1315 | 91.5% | 90.8% | NEW |
| 9 | Gemini 2.5 Flash | 1305 | 90.8% | 89.5% | NEW | |
| 10 | Grok-3 | xAI | 1298 | 90.5% | 89.2% | - |
| 11 | Llama 4 70B | Meta | 1285 | 89.2% | 88% | NEW |
| 12 | Qwen 3 Max | Alibaba | 1278 | 89% | 88.5% | + |
| 13 | Mistral Large 3 | Mistral AI | 1270 | 88.5% | 87.8% | - |
| 14 | Claude Haiku 4.5 | Anthropic | 1255 | 87.8% | 86.5% | - |
AI Tools by Category
Coding Assistant
- 1Claude Code
- 2Cursor
- 3GitHub Copilot
- 4Windsurf
- 5Cody
Chatbot
- 1Claude.ai
- 2ChatGPT
- 3Gemini
- 4Perplexity
- 5Poe
Image Generation
- 1Midjourney v7
- 2DALL-E 4
- 3Flux 1.1 Pro
- 4Stable Diffusion 4
- 5Ideogram 3
Writing & Content
- 1Jasper
- 2Notion AI
- 3Copy.ai
- 4Writesonic
- 5Grammarly
Video Generation
- 1Runway Gen-4
- 2Sora
- 3Kling 2.0
- 4Pika 2.0
- 5Haiper
Research & Search
- 1Perplexity AI
- 2NotebookLM
- 3Elicit
- 4Consensus
- 5Semantic Scholar
Automation & Workflow
- 1n8n
- 2Dify
- 3Zapier AI
- 4Make AI
- 5LangFlow
Audio & Voice
- 1ElevenLabs
- 2Suno v4
- 3Udio
- 4Play.ht
- 5Murf AI