Updated: Nov 9, 2025, 09:28 PM
Explore top AI models ranked by community votes and performance metrics
Total models
14
Available in database
Top model
Deepseek V2.5 (FIM)
Ranked #1
Top score
1028
Highest score
| # | Model | Score | Votes | Confidence interval | Organization |
|---|---|---|---|---|---|
| 🥇 | Deepseek V2.5 (FIM) | 1028.00 | 2,292 | ±15 | Deepseek A |
| 🥇 | Claude 3.5 Sonnet (06/20) | 1012.00 | 3,544 | ±11 | Anthropic |
| 🥇 | Claude 3.5 Sonnet (10/22) | 1004.00 | 3,596 | ±12 | Anthropic |
| 🥇 | Codestral (25.01) | 1001.00 | 2,180 | ±13 | Mistral |
| 🥈 | Codestral (05/24) | 1001.00 | 5,744 | ±6 | Mistral |
| 🥇 | Qwen-2.5-Coder (FiM) | 998.00 | 3,401 | ±16 | Alibaba |
| 🥇 | Mercury Coder Mini | 994.00 | 1,430 | ±19 | Inception |
| 🥉 | Gemini-1.5-Pro-002 | 986.00 | 3,441 | ±10 | |
| 🥉 | GPT-4o (08/06) | 986.00 | 4,464 | ±11 | OpenAI |
| 4 | Meta-Llama-3.1-405B-Instruct | 984.00 | 3,432 | ±10 | Meta |
| 5 | Gemini-1.5-Flash-002 | 977.00 | 5,191 | ±11 | |
| 7 | Meta-Llama-3.1-70B-Instruct | 969.00 | 4,085 | ±11 | Meta |
| 13 | Qwen2.5-Coder-32B-Instruct | 950.00 | 4,400 | ±8 | Alibaba |
| 13 | GPT-4o-mini (07/18) | 943.00 | 4,776 | ±10 | OpenAI |
Updated hourly • Showing 14 / 14 models
Source: LM BASE