AI Model Leaderboard
Compare top AI models across multiple dimensions
1
claude-fable-5
#1
Overall
2
claude-opus-4-6-thinking
#2
Overall
3
claude-opus-4-7-thinking
#3
Overall
| Rank | Model | Overall | Expert | Hard Prompts | Coding | Math | Creative Writing | Instruction Following | Longer Query | Updated |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | claude-fable-5 | 1 | 3 | 1 | 1 | 2 | 1 | 1 | - | 2026-07-08 |
| 2 | claude-opus-4-6-thinking | 2 | 1 | 2 | 3 | 1 | 2 | 2 | - | 2026-07-08 |
| 3 | claude-opus-4-7-thinking | 3 | 5 | 4 | 2 | 5 | 3 | 4 | - | 2026-07-08 |
| 4 | claude-opus-4-6 | 4 | 4 | 3 | 5 | 4 | 7 | 4 | - | 2026-07-08 |
| 5 | claude-opus-4-7 | 5 | 2 | 5 | 4 | 9 | 5 | 6 | - | 2026-07-08 |
| 6 | muse-spark | 6 | 33 | 9 | 11 | 33 | 11 | 24 | 31 | 2026-07-08 |
| 7 | gemini-3.1-pro-preview | 7 | 12 | 8 | 14 | 11 | 6 | 9 | 8 | 2026-07-08 |
| 8 | gemini-3-pro | 8 | 19 | 11 | 18 | 17 | 4 | 14 | 13 | 2026-07-08 |
| 9 | claude-opus-4-8-thinking | 9 | 6 | 6 | 7 | 6 | 10 | 5 | 7 | 2026-07-08 |
| 10 | gpt-5.5-high | 10 | 10 | 13 | 19 | 12 | 21 | 12 | 16 | 2026-07-08 |
| 11 | gemini-3.5-flash | 11 | 20 | 20 | 35 | 3 | 8 | 26 | 26 | 2026-07-08 |
| 12 | gpt-5.4-high | 12 | 8 | 12 | 15 | 7 | 27 | 11 | 19 | 2026-07-08 |
| 13 | claude-opus-4-8 | 13 | 9 | 7 | 6 | 15 | 12 | 8 | 6 | 2026-07-08 |
| 14 | gpt-5.2-chat-latest-20260210 | 14 | 28 | 16 | 20 | 41 | 42 | 29 | 33 | 2026-07-08 |
| 15 | qwen3.7-max-preview | 15 | 14 | 18 | 10 | 10 | 29 | 18 | 9 | 2026-07-08 |
| 16 | gpt-5.5 | 16 | 15 | 21 | 38 | 8 | 25 | 16 | 25 | 2026-07-08 |
| 17 | grok-4.20-beta-0309-reasoning | 17 | 51 | 25 | 24 | 23 | 26 | 38 | 38 | 2026-07-08 |
| 18 | grok-4.20-beta1 | 18 | 53 | 31 | 36 | 43 | 14 | 40 | 43 | 2026-07-08 |
| 19 | gemini-3-flash | 19 | 26 | 23 | 34 | 20 | 15 | 28 | 28 | 2026-07-08 |
| 20 | claude-opus-4-5-20251101-thinking-32k | 20 | 16 | 14 | 8 | 27 | 9 | 7 | 10 | 2026-07-08 |
| 21 | gpt-5.5-instant | 21 | 44 | 27 | 26 | 31 | 17 | 33 | 32 | 2026-07-08 |
| 22 | glm-5.1 | 22 | 23 | 17 | 12 | 19 | 16 | 20 | 15 | 2026-07-08 |
| 23 | claude-sonnet-4-6 | 23 | 13 | 10 | 9 | 32 | 20 | 10 | 11 | 2026-07-08 |
| 24 | grok-4.20-multi-agent-beta-0309 | 24 | 46 | 34 | 33 | 45 | 23 | 46 | 46 | 2026-07-08 |
| 25 | claude-opus-4-5-20251101 | 25 | 18 | 15 | 13 | 30 | 13 | 13 | 12 | 2026-07-08 |
| 26 | glm-5.2 (max) | 26 | 21 | 26 | 21 | 24 | 31 | 19 | 23 | 2026-07-08 |
| 27 | ernie-5.1 | 27 | 31 | 32 | 29 | 16 | 44 | 36 | 42 | 2026-07-08 |
| 28 | gpt-5.4 | 28 | 27 | 28 | 23 | 35 | 40 | 23 | 24 | 2026-07-08 |
| 29 | mimo-v2.5-pro | 29 | 11 | 19 | 17 | 14 | 39 | 15 | 14 | 2026-07-08 |
| 30 | grok-4.1-thinking | 30 | 59 | 42 | 47 | 52 | 49 | 61 | 62 | 2026-07-08 |
| 31 | qwen3.5-max-preview | 31 | 24 | 24 | 31 | 28 | 19 | 17 | 22 | 2026-07-08 |
| 32 | claude-sonnet-5-high | 32 | 7 | 22 | 22 | 34 | 41 | 25 | 21 | 2026-07-08 |
| 33 | qwen3.7-plus | 33 | 32 | 33 | 30 | 22 | 33 | 32 | 30 | 2026-07-08 |
| 34 | kimi-k2.6 | 34 | 17 | 30 | 28 | 13 | 43 | 30 | 27 | 2026-07-08 |
| 35 | qwen3.6-max-preview | 35 | 25 | 36 | 37 | 18 | 37 | 39 | 29 | 2026-07-08 |
| 36 | gemini-3-flash (thinking-minimal) | 36 | 60 | 44 | 55 | 37 | 22 | 44 | 44 | 2026-07-08 |
| 37 | grok-4.1 | 37 | 73 | 47 | 56 | 72 | 45 | 60 | 57 | 2026-07-08 |
| 38 | deepseek-v4-pro | 38 | 38 | 39 | 44 | 51 | 36 | 35 | 35 | 2026-07-08 |
| 39 | glm-5 | 39 | 35 | 40 | 48 | 54 | 28 | 42 | 37 | 2026-07-08 |
| 40 | deepseek-v4-pro-thinking | 40 | 49 | 43 | 53 | 21 | 34 | 37 | 36 | 2026-07-08 |
| 41 | claude-sonnet-4-5-20250929-thinking-32k | 41 | 22 | 29 | 16 | 38 | 24 | 21 | 17 | 2026-07-08 |
| 42 | claude-sonnet-4-5-20250929 | 42 | 34 | 35 | 25 | 75 | 18 | 22 | 20 | 2026-07-08 |
| 43 | dola-seed-2.0-pro | 43 | 41 | 38 | 32 | 44 | 71 | 58 | 54 | 2026-07-08 |
| 44 | gpt-5.1-high | 44 | 42 | 46 | 58 | 39 | 48 | 41 | 45 | 2026-07-08 |
| 45 | gemma-4-31b | 45 | 37 | 48 | 49 | 26 | 54 | 34 | 40 | 2026-07-08 |
| 46 | kimi-k2.5-thinking | 46 | 43 | 51 | 43 | 25 | 50 | 49 | 47 | 2026-07-08 |
| 47 | gpt-5.4-mini-high | 47 | 40 | 50 | 51 | 58 | 73 | 54 | 61 | 2026-07-08 |
| 48 | claude-opus-4-1-20250805-thinking-16k | 48 | 36 | 37 | 27 | 49 | 30 | 27 | 18 | 2026-07-08 |
| 49 | ernie-5.0-preview-1203 | 49 | 77 | 56 | 82 | 110 | 55 | 74 | 83 | 2026-07-08 |
| 50 | gpt-5.3-chat-latest | 50 | 57 | 49 | 50 | 81 | 69 | 56 | 49 | 2026-07-08 |
| 51 | mimo-v2-pro | 51 | 30 | 45 | 41 | 42 | 51 | 43 | 39 | 2026-07-08 |
| 52 | claude-opus-4-1-20250805 | 52 | 61 | 41 | 39 | 67 | 35 | 31 | 34 | 2026-07-08 |
| 53 | ernie-5.0-0110 | 53 | 85 | 54 | 59 | 63 | 53 | 68 | 75 | 2026-07-08 |
| 54 | minimax-m3 | 54 | 48 | 53 | 45 | 53 | 67 | 47 | 52 | 2026-07-08 |
| 55 | gemini-2.5-pro | 55 | 65 | 66 | 91 | 56 | 32 | 48 | 48 | 2026-07-08 |
| 56 | gpt-4.5-preview-2025-02-27 | 56 | 106 | 90 | 100 | 107 | 38 | 51 | 70 | 2026-07-08 |
| 57 | grok-4.3 | 57 | 87 | 69 | 64 | 87 | 46 | 88 | 63 | 2026-07-08 |
| 58 | qwen3.6-plus | 58 | 47 | 52 | 52 | 40 | 64 | 52 | 50 | 2026-07-08 |
| 59 | chatgpt-4o-latest-20250326 | 59 | 105 | 71 | 84 | 116 | 52 | 64 | 77 | 2026-07-08 |
| 60 | qwen3.5-397b-a17b | 60 | 39 | 55 | 54 | 48 | 62 | 57 | 51 | 2026-07-08 |
| 61 | glm-4.7 | 61 | 84 | 58 | 65 | 74 | 66 | 63 | 53 | 2026-07-08 |
| 62 | gpt-5.1 | 62 | 70 | 72 | 79 | 85 | 61 | 65 | 69 | 2026-07-08 |
| 63 | gemma-4-26b-a4b | 63 | 50 | 59 | 70 | 29 | 74 | 50 | 60 | 2026-07-08 |
| 64 | gpt-5.2-high | 64 | 45 | 64 | 60 | 36 | 97 | 66 | 84 | 2026-07-08 |
| 65 | deepseek-v4-flash-thinking | 65 | 55 | 68 | 73 | 61 | 63 | 55 | 59 | 2026-07-08 |
| 66 | deepseek-v4-flash | 66 | 69 | 62 | 68 | 80 | 59 | 62 | 56 | 2026-07-08 |
| 67 | longcat-flash-chat-2602-exp | 67 | 63 | 63 | 42 | 64 | 92 | 86 | 79 | 2026-07-08 |
| 68 | gpt-5.2 | 68 | 62 | 61 | 66 | 66 | 93 | 70 | 76 | 2026-07-08 |
| 69 | qwen3-max-preview | 69 | 58 | 65 | 67 | 59 | 85 | 69 | 68 | 2026-07-08 |
| 70 | gpt-5-high | 70 | 68 | 83 | 87 | 65 | 114 | 92 | 115 | 2026-07-08 |
| 71 | mimo-v2.5 | 71 | 52 | 57 | 57 | 50 | 84 | 59 | 55 | 2026-07-08 |
| 72 | gemini-3.1-flash-lite-preview | 72 | 89 | 85 | 105 | 57 | 58 | 94 | 91 | 2026-07-08 |
| 73 | kimi-k2.5-instant | 73 | 72 | 60 | 40 | 55 | 95 | 53 | 67 | 2026-07-08 |
| 74 | grok-4-1-fast-reasoning | 74 | 91 | 89 | 96 | 93 | 57 | 106 | 99 | 2026-07-08 |
| 75 | o3-2025-04-16 | 75 | 88 | 92 | 102 | 47 | 102 | 105 | 120 | 2026-07-08 |
| 76 | mimo-v2-omni | 76 | 67 | 67 | 61 | 62 | 80 | 67 | 58 | 2026-07-08 |
| 77 | kimi-k2-thinking-turbo | 77 | 66 | 73 | 63 | 60 | 88 | 77 | 85 | 2026-07-08 |
| 78 | amazon-nova-experimental-chat-26-02-10 | 78 | 29 | 74 | 62 | 77 | 148 | 78 | 93 | 2026-07-08 |
| 79 | gpt-5-chat | 79 | 82 | 75 | 95 | 99 | 90 | 79 | 80 | 2026-07-08 |
| 80 | mistral-medium-3.5 | 80 | 92 | 86 | 74 | 68 | 82 | 73 | 88 | 2026-07-08 |
| 81 | glm-4.6 | 81 | 90 | 88 | 101 | 88 | 72 | 84 | 86 | 2026-07-08 |
| 82 | deepseek-v3.2 | 82 | 78 | 80 | 83 | 70 | 76 | 71 | 73 | 2026-07-08 |
| 83 | deepseek-v3.2-exp-thinking | 83 | 76 | 81 | 77 | 76 | 83 | 80 | 89 | 2026-07-08 |
| 84 | claude-opus-4-20250514-thinking-16k | 84 | 83 | 70 | 46 | 89 | 47 | 45 | 41 | 2026-07-08 |
| 85 | qwen3-max-2025-09-23 | 85 | 119 | 76 | 78 | 69 | 86 | 83 | 87 | 2026-07-08 |
| 86 | qwen3-235b-a22b-instruct-2507 | 86 | 75 | 77 | 80 | 90 | 107 | 82 | 81 | 2026-07-08 |
| 87 | deepseek-v3.2-thinking | 87 | 74 | 82 | 75 | 82 | 91 | 75 | 71 | 2026-07-08 |
| 88 | deepseek-v3.2-exp | 88 | 110 | 78 | 90 | 92 | 60 | 81 | 72 | 2026-07-08 |
| 89 | deepseek-r1-0528 | 89 | 114 | 99 | 92 | 130 | 87 | 118 | 121 | 2026-07-08 |
| 90 | grok-4-fast-chat | 90 | 111 | 100 | 104 | 84 | 100 | 109 | 102 | 2026-07-08 |
| 91 | nvidia-nemotron-3-ultra-550b-a55b-nvfp4 | 91 | 56 | 96 | 88 | 46 | 109 | 102 | 90 | 2026-07-08 |
| 92 | ernie-5.0-preview-1022 | 92 | 99 | 109 | 140 | 123 | 68 | 110 | 104 | 2026-07-08 |
| 93 | deepseek-v3.1-terminus-thinking | 93 | - | 84 | 94 | 108 | 99 | 72 | 66 | 2026-07-08 |
| 94 | kimi-k2-0905-preview | 94 | 118 | 97 | 85 | 94 | 104 | 119 | 126 | 2026-07-08 |
| 95 | kimi-k2-0711-preview | 95 | 123 | 105 | 97 | 139 | 119 | 138 | 136 | 2026-07-08 |
| 96 | deepseek-v3.1 | 96 | 107 | 103 | 116 | 96 | 96 | 100 | 103 | 2026-07-08 |
| 97 | deepseek-v3.1-thinking | 97 | 103 | 95 | 106 | 98 | 70 | 76 | 65 | 2026-07-08 |
| 98 | qwen3.5-122b-a10b | 98 | 86 | 101 | 99 | 83 | 122 | 96 | 107 | 2026-07-08 |
| 99 | minimax-m2.7 | 99 | 80 | 87 | 69 | 86 | 126 | 93 | 82 | 2026-07-08 |
| 100 | amazon-nova-experimental-chat-26-01-10 | 100 | 54 | 79 | 71 | 105 | 135 | 103 | 101 | 2026-07-08 |
Data updated: 2026-07-08 | Source: arena.ai/leaderboard — Chatbot Arena leaderboard rankings (663 models tracked).