AI Leaderboards
Compare the best AI models across different benchmarks and tasks.
🏆 Open LLM Leaderboard
Ranking of open-source language models on various benchmarks
| Rank | Model | Organization | Score | Link |
|---|---|---|---|---|
| 1 | Qwen2.5-72B-Instruct | Alibaba | 75.3 | View → |
| 2 | Llama-3.1-70B-Instruct | Meta | 73.8 | View → |
| 3 | Mistral-Large-Instruct | Mistral AI | 72.1 | View → |
| 4 | Command-R+ | Cohere | 70.5 | View → |
| 5 | Yi-Large-Instruct | 01.AI | 69.8 | View → |
📊 MTEB Leaderboard
Massive Text Embedding Benchmark - Best embedding models
🖼️ VLMEvalKit Leaderboard
Vision-Language Models benchmark
| Rank | Model | Score | Link |
|---|---|---|---|
| 1 | GPT-4o | 78.9 | - |
| 2 | Claude-3.5-Sonnet | 76.2 | - |
| 3 | Qwen2-VL-72B | 74.5 | View → |