AI Model Leaderboard
Model performance ranking across coding, reasoning, math and vision benchmarks.
| Rank | Model | Provider | Coding | Reasoning | Math | Vision |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 4 | Anthropic | 93 | 95 | 91 | — |
| 2 | o3 | OpenAI | 89 | 96 | 94 | — |
| 3 | Gemini 2.5 Pro | 90 | 93 | 92 | 94 | |
| 4 | GPT-4.1 | OpenAI | 92 | 91 | 89 | — |
| 5 | Claude Sonnet 4 | Anthropic | 90 | 92 | — | 88 |
| 6 | GPT-4o | OpenAI | 88 | 90 | — | 92 |
| 7 | DeepSeek Reasoner | DeepSeek | 85 | 93 | 90 | — |
| 8 | Gemini 2.5 Flash | 84 | 86 | — | 90 | |
| 9 | DeepSeek Chat | DeepSeek | 87 | 85 | 83 | — |
| 10 | Qwen3 235B | Alibaba | — | — | — | — |
| 11 | Qwen3 32B | Alibaba | — | — | — | — |
| 12 | Qwen3 Coder 480B | Alibaba | — | — | — | — |
| 13 | Claude 3.5 Sonnet | Anthropic | — | — | — | — |
| 14 | Claude 3.7 Sonnet | Anthropic | — | — | — | — |
| 15 | Claude Haiku 3.5 | Anthropic | — | — | — | — |
| 16 | Claude Haiku 4.5 | Anthropic | — | — | — | — |
| 17 | Claude Opus 4.8 | Anthropic | — | — | — | — |
| 18 | Claude Opus 5 | Anthropic | — | — | — | — |
| 19 | Claude Sonnet 4.6 | Anthropic | — | — | — | — |
| 20 | Claude Sonnet 5 | Anthropic | — | — | — | — |
| 21 | ERNIE 4.5 VL 424B | Baidu | — | — | — | — |
| 22 | Doubao 1.5 Pro | ByteDance | — | — | — | — |
| 23 | DeepSeek V4-Flash | DeepSeek | — | — | — | — |
| 24 | DeepSeek V4-Pro | DeepSeek | — | — | — | — |
| 25 | Gemini 1.5 Pro | — | — | — | — | |
| 26 | Gemini 2.0 Flash | — | — | — | — | |
| 27 | Gemini 2.5 Flash-Lite | — | — | — | — | |
| 28 | Gemini 3 Flash | — | — | — | — | |
| 29 | Gemini 3.1 Flash-Lite | — | — | — | — | |
| 30 | Gemini 3.1 Pro | — | — | — | — | |
| 31 | Llama 4 Maverick | Meta | — | — | — | — |
| 32 | Llama 4 Scout | Meta | — | — | — | — |
| 33 | MiniMax M3 | MiniMax | — | — | — | — |
| 34 | Mistral Large 2 | Mistral | — | — | — | — |
| 35 | Mistral Large 3 | Mistral | — | — | — | — |
| 36 | Mistral Small 4 | Mistral | — | — | — | — |
| 37 | Kimi K2 | Moonshot | — | — | — | — |
| 38 | Kimi K2.5 | Moonshot | — | — | — | — |
| 39 | Kimi K2.6 | Moonshot | — | — | — | — |
| 40 | GPT-4.1 mini | OpenAI | — | — | — | — |
| 41 | GPT-4.1 nano | OpenAI | — | — | — | — |
| 42 | GPT-4o mini | OpenAI | — | — | — | — |
| 43 | GPT-5.4 | OpenAI | — | — | — | — |
| 44 | GPT-5.5 | OpenAI | — | — | — | — |
| 45 | o4-mini | OpenAI | — | — | — | — |
| 46 | Hunyuan TurboS | Tencent | — | — | — | — |
| 47 | Grok 4 | xAI | — | — | — | — |
| 48 | GLM-4.5 | Zhipu | — | — | — | — |
| 49 | GLM-4.6 | Zhipu | — | — | — | — |
Anthropic
- Coding
- 93
- Reasoning
- 95
- Math
- 91
- Vision
- —
- o3#2
OpenAI
- Coding
- 89
- Reasoning
- 96
- Math
- 94
- Vision
- —
Google
- Coding
- 90
- Reasoning
- 93
- Math
- 92
- Vision
- 94
- GPT-4.1#4
OpenAI
- Coding
- 92
- Reasoning
- 91
- Math
- 89
- Vision
- —
Anthropic
- Coding
- 90
- Reasoning
- 92
- Math
- —
- Vision
- 88
- GPT-4o#6
OpenAI
- Coding
- 88
- Reasoning
- 90
- Math
- —
- Vision
- 92
DeepSeek
- Coding
- 85
- Reasoning
- 93
- Math
- 90
- Vision
- —
Google
- Coding
- 84
- Reasoning
- 86
- Math
- —
- Vision
- 90
DeepSeek
- Coding
- 87
- Reasoning
- 85
- Math
- 83
- Vision
- —
- Qwen3 235B#10
Alibaba
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- Qwen3 32B#11
Alibaba
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Alibaba
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Anthropic
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Baidu
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
ByteDance
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
DeepSeek
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
DeepSeek
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Google
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Google
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Google
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Google
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Google
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Google
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Meta
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Meta
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- MiniMax M3#33
MiniMax
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Mistral
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Mistral
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Mistral
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- Kimi K2#37
Moonshot
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- Kimi K2.5#38
Moonshot
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- Kimi K2.6#39
Moonshot
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- GPT-4.1 mini#40
OpenAI
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- GPT-4.1 nano#41
OpenAI
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- GPT-4o mini#42
OpenAI
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- GPT-5.4#43
OpenAI
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- GPT-5.5#44
OpenAI
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- o4-mini#45
OpenAI
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
Tencent
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- Grok 4#47
xAI
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- GLM-4.5#48
Zhipu
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —
- GLM-4.6#49
Zhipu
- Coding
- —
- Reasoning
- —
- Math
- —
- Vision
- —