AI Model Leaderboard
Live rankings across 50 models. Sorted by overall.
| # | Model | Provider | Overall | Coding | Reasoning | Writing | Vision | Context | Input | Output | Latency | Released |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude 4 Opus | Anthropic | 96 | 97 | 97 | 96 | 93 | 200K | $15.00 | $75.00 | reasoning | |
| 2 | GPT-5 | OpenAI | 95 | 95 | 96 | 94 | 96 | 400K | $5.00 | $20.00 | standard | |
| 3 | Claude Opus 4.1 | Anthropic | 95 | 96 | 97 | 96 | 90 | 200K | $15.00 | $75.00 | reasoning | |
| 4 | Claude 4 Sonnet | Anthropic | 94 | 96 | 94 | 95 | 92 | 200K | $3.00 | $15.00 | standard | |
| 5 | Gemini 2.5 Pro | 94 | 93 | 95 | 91 | 97 | 1M | $1.25 | $10.00 | standard | ||
| 6 | Gemini 3 Pro | 94 | 93 | 95 | 92 | 96 | 1M | $3.60 | $14.00 | standard | ||
| 7 | Claude 3.7 Sonnet | Anthropic | 93 | 95 | 93 | 93 | 90 | 200K | $3.00 | $15.00 | standard | |
| 8 | GPT-4.1 | OpenAI | 92 | 94 | 92 | 93 | 90 | 1M | $2.00 | $8.00 | standard | |
| 9 | Gemini 3.6 Flash | 92 | 91 | 92 | 90 | 94 | 1M | $1.50 | $7.50 | fast | ||
| 10 | Claude Sonnet 4.5 | Anthropic | 92 | 95 | 93 | 93 | 88 | 200K | $3.00 | $15.00 | fast | |
| 11 | GPT-4o | OpenAI | 91 | 90 | 88 | 92 | 95 | 128K | $2.50 | $10.00 | fast | |
| 12 | Claude 3.5 Sonnet | Anthropic | 91 | 92 | 90 | 94 | 88 | 200K | $3.00 | $15.00 | standard | |
| 13 | Kimi K3 | Moonshot AI | 91 | 93 | 94 | 90 | 88 | 1M | $3.00 | $15.00 | standard | |
| 14 | Gemini 2.5 Flash | 90 | 88 | 89 | 87 | 94 | 1M | $0.15 | $0.60 | fast | ||
| 15 | Claude 3 Opus | Anthropic | 90 | 90 | 91 | 93 | 85 | 200K | $15.00 | $75.00 | standard | |
| 16 | Grok 4 | xAI | 89 | 90 | 91 | 88 | 85 | 256K | $3.00 | $15.00 | fast | |
| 17 | Grok 3 | xAI | 88 | 91 | 92 | 88 | 82 | 131.1K | $3.00 | $15.00 | standard | |
| 18 | OpenAI o3 | OpenAI | 88 | 95 | 97 | 90 | 70 | 200K | $10.00 | $40.00 | reasoning | |
| 19 | Gemini 2.0 Flash | 87 | 85 | 86 | 84 | 92 | 1M | $0.10 | $0.40 | fast | ||
| 20 | Gemini 1.5 Pro | 87 | 86 | 87 | 85 | 88 | 2.1M | $1.25 | $5.00 | standard | ||
| 21 | OpenAI o4 Mini | OpenAI | 86 | 92 | 93 | 84 | 75 | 200K | $1.10 | $4.40 | reasoning | |
| 22 | Llama 4 Maverick | Meta | 86 | 87 | 88 | 82 | 85 | 1M | $0.20 | $0.60 | standard | |
| 23 | GPT-5 Mini | OpenAI | 86 | 89 | 88 | 87 | 80 | 400K | $0.40 | $1.60 | fast | |
| 24 | GPT-4.1 Mini | OpenAI | 85 | 88 | 85 | 86 | 82 | 1M | $0.40 | $1.60 | fast | |
| 25 | Mistral Large | Mistral | 85 | 86 | 87 | 88 | 78 | 128K | $2.00 | $6.00 | standard | |
| 26 | Pixtral Large | Mistral | 85 | 83 | 84 | 80 | 93 | 128K | $2.00 | $6.00 | standard | |
| 27 | Claude 4 Haiku | Anthropic | 83 | 83 | 84 | 86 | 78 | 200K | $0.80 | $4.00 | fast | |
| 28 | Grok 2 | xAI | 83 | 84 | 85 | 83 | 80 | 131.1K | $2.00 | $10.00 | standard | |
| 29 | Llama 4 Scout | Meta | 82 | 83 | 85 | 79 | 82 | 10M | $0.15 | $0.50 | standard | |
| 30 | Command A | Cohere | 82 | 84 | 86 | 87 | 72 | 256K | $2.50 | $10.00 | standard | |
| 31 | OpenAI o1 | OpenAI | 79 | 93 | 96 | 88 | 40 | 200K | $15.00 | $60.00 | reasoning | |
| 32 | Claude 3.5 Haiku | Anthropic | 79 | 78 | 80 | 82 | 75 | 200K | $0.80 | $4.00 | fast | |
| 33 | DeepSeek V3 0324 | DeepSeek | 79 | 92 | 91 | 86 | 45 | 128K | $0.27 | $1.10 | standard | |
| 34 | GPT-4o Mini | OpenAI | 78 | 82 | 78 | 80 | 70 | 128K | $0.15 | $0.60 | fast | |
| 35 | DeepSeek V3 | DeepSeek | 78 | 91 | 90 | 85 | 45 | 64K | $0.27 | $1.10 | standard | |
| 36 | Grok 3 Mini | xAI | 77 | 79 | 80 | 78 | 70 | 131.1K | $0.30 | $0.50 | fast | |
| 37 | Command R+ | Cohere | 77 | 82 | 84 | 86 | 55 | 128K | $2.50 | $10.00 | standard | |
| 38 | DeepSeek R1 | DeepSeek | 77 | 94 | 95 | 82 | 35 | 64K | $0.55 | $2.19 | reasoning | |
| 39 | Gemini 2.0 Flash Lite | 76 | 72 | 74 | 76 | 80 | 1M | $0.075 | $0.30 | fast | ||
| 40 | Kimi K2 | Moonshot AI | 76 | 90 | 88 | 86 | 40 | 131.1K | $0.60 | $2.50 | fast | |
| 41 | OpenAI o3 Mini | OpenAI | 75 | 90 | 91 | 82 | 35 | 200K | $1.10 | $4.40 | reasoning | |
| 42 | DeepSeek V4 | DeepSeek | 75 | 92 | 90 | 84 | 35 | 163.8K | $0.30 | $1.20 | fast | |
| 43 | Llama 3.1 405B | Meta | 74 | 85 | 86 | 83 | 40 | 128K | $0.35 | $0.70 | slow | |
| 44 | Llama 3.3 70B | Meta | 73 | 84 | 82 | 80 | 45 | 128K | $0.23 | $0.40 | standard | |
| 45 | GPT-4.1 Nano | OpenAI | 70 | 75 | 72 | 74 | 60 | 1M | $0.10 | $0.40 | fast | |
| 46 | Mistral Small | Mistral | 69 | 77 | 76 | 79 | 45 | 32K | $0.10 | $0.30 | fast | |
| 47 | Command R | Cohere | 69 | 76 | 78 | 80 | 40 | 128K | $0.15 | $0.60 | fast | |
| 48 | Codestral | Mistral | 68 | 94 | 78 | 70 | 30 | 256K | $0.30 | $0.90 | fast | |
| 49 | Ministral 8B | Mistral | 65 | 72 | 68 | 70 | 50 | 128K | $0.10 | $0.10 | fast | |
| 50 | DeepSeek Coder V2 | DeepSeek | 64 | 93 | 72 | 65 | 25 | 128K | $0.14 | $0.28 | fast |
