作舟知识辅助
AI 榜单
从智能体、聊天、编程、图像和视频五类榜单出发,找到值得亲自试用的模型。排名只是参考,最终选择仍取决于你的任务与预算。
Coding
编程
来自 Arena 文本榜的编程分类,反映用户对编程回答的偏好。它不等同于编程代理完成软件工程任务的能力。
每日同步正常
左右滚动查看全部字段。数值保留两位小数,悬停可查看原始精度;原始分类和数据日期按来源保留。
| 排名 | 模型 | 开发方 | 模型许可证 | Arena 分数 | 置信下界 | 置信上界 | 评分方差 | 对战次数 | 原始分类 | 数据发布日期 |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon (High) | Proprietary | 1,559.33 | 1,542.2 | 1,576.46 | 76.38 | 1,231 | coding | 2026-10-15 | |
| 2 | Claude Fable 5 (High) | anthropic | Proprietary | 1,550.65 | 1,544.05 | 1,557.25 | 11.35 | 10,844 | coding | 2026-10-15 |
| 3 | Claude Opus 4.7 (High) | anthropic | Proprietary | 1,550.57 | 1,544.73 | 1,556.42 | 8.9 | 18,573 | coding | 2026-10-15 |
| 4 | Claude Opus 4.6 (High) | anthropic | Proprietary | 1,548.29 | 1,542.85 | 1,553.72 | 7.68 | 21,082 | coding | 2026-10-15 |
| 5 | Muse Wonder (Max) | meta | Proprietary | 1,547.97 | 1,527.07 | 1,568.87 | 113.69 | 776 | coding | 2026-10-15 |
| 6 | Claude Opus 5.5 (High) | anthropic | Proprietary | 1,547.52 | 1,533.61 | 1,561.44 | 50.41 | 1,894 | coding | 2026-10-15 |
| 7 | Claude Opus 4.6 | anthropic | Proprietary | 1,547.15 | 1,541.95 | 1,552.35 | 7.05 | 23,838 | coding | 2026-10-15 |
| 8 | Claude Opus 4.7 | anthropic | Proprietary | 1,546.31 | 1,540.51 | 1,552.11 | 8.76 | 18,806 | coding | 2026-10-15 |
| 9 | gpt-6-astra-max | openai | Proprietary | 1,543.4 | 1,531.78 | 1,555.02 | 35.14 | 2,744 | coding | 2026-10-15 |
| 10 | gpt-6.1-sol-max | openai | Proprietary | 1,539.79 | 1,522.63 | 1,556.95 | 76.62 | 1,257 | coding | 2026-10-15 |
| 11 | Muse Spark 1.2 (xHigh) | meta | Proprietary | 1,539.25 | 1,526.2 | 1,552.31 | 44.37 | 2,170 | coding | 2026-10-15 |
| 12 | Kimi K3 (Max) | moonshot | Kimi K3 license | 1,537.83 | 1,530.58 | 1,545.09 | 13.69 | 8,306 | coding | 2026-10-15 |
| 13 | mimo-v2.6-pro | xiaomi | MIT | 1,537.58 | 1,519.93 | 1,555.23 | 81.1 | 1,105 | coding | 2026-10-15 |
| 14 | Claude Fable 5.1 (Max) | anthropic | Proprietary | 1,537.14 | 1,525.77 | 1,548.52 | 33.68 | 2,900 | coding | 2026-10-15 |
| 15 | Muse Spark 1.3 (Max) | meta | Proprietary | 1,534.83 | 1,525.51 | 1,544.14 | 22.58 | 4,556 | coding | 2026-10-15 |
| 16 | gpt-5.6-sol-xhigh | openai | Proprietary | 1,534.18 | 1,527.45 | 1,540.91 | 11.8 | 10,825 | coding | 2026-10-15 |
| 17 | claude-opus-4-8-high | anthropic | Proprietary | 1,533.53 | 1,527.72 | 1,539.33 | 8.78 | 17,427 | coding | 2026-10-15 |
| 18 | Claude Opus 5 (High) | anthropic | Proprietary | 1,532.65 | 1,526.57 | 1,538.72 | 9.6 | 17,248 | coding | 2026-10-15 |
| 19 | Muse Spark 1.1 | meta | Proprietary | 1,532.53 | 1,526.06 | 1,539 | 10.9 | 11,856 | coding | 2026-10-15 |
| 20 | claude-opus-4-5-20251101-high-32k | anthropic | Proprietary | 1,530.67 | 1,523.45 | 1,537.89 | 13.58 | 7,804 | coding | 2026-10-15 |
| 21 | claude-sonnet-5.5-xhigh | anthropic | Proprietary | 1,530.34 | 1,515.34 | 1,545.34 | 58.56 | 1,627 | coding | 2026-10-15 |
| 22 | Claude Opus 5 (Max) | anthropic | Proprietary | 1,529.4 | 1,521.89 | 1,536.92 | 14.72 | 8,148 | coding | 2026-10-15 |
| 23 | claude-opus-4-8 | anthropic | Proprietary | 1,529.23 | 1,523.44 | 1,535.01 | 8.71 | 18,069 | coding | 2026-10-15 |
| 24 | Muse Spark | meta | Proprietary | 1,528.61 | 1,518.71 | 1,538.51 | 25.52 | 3,946 | coding | 2026-10-15 |
| 25 | claude-sonnet-4-6 | anthropic | Proprietary | 1,528.4 | 1,522.78 | 1,534.01 | 8.21 | 19,724 | coding | 2026-10-15 |
| 26 | Gemini 3.8 Flash (High) | Proprietary | 1,527.73 | 1,520.62 | 1,534.84 | 13.15 | 9,810 | coding | 2026-10-15 | |
| 27 | glm-5.3-flash | zai | MIT | 1,524.53 | 1,517.07 | 1,531.99 | 14.48 | 8,457 | coding | 2026-10-15 |
| 28 | qwen3.7-max-preview | alibaba | Proprietary | 1,523.74 | 1,505.72 | 1,541.76 | 84.52 | 1,163 | coding | 2026-10-15 |
| 29 | deepseek-v4.1-flash-max | deepseek | MIT | 1,523.37 | 1,513.1 | 1,533.65 | 27.49 | 3,527 | coding | 2026-10-15 |
| 30 | qwen3.8-max | alibaba | Proprietary | 1,523.36 | 1,515.79 | 1,530.93 | 14.92 | 7,677 | coding | 2026-10-15 |
| 31 | claude-opus-4-5-20251101 | anthropic | Proprietary | 1,522.76 | 1,517.37 | 1,528.14 | 7.55 | 17,986 | coding | 2026-10-15 |
| 32 | mimo-v2.5-pro | xiaomi | MIT | 1,521.61 | 1,516.1 | 1,527.12 | 7.9 | 20,404 | coding | 2026-10-15 |
| 33 | Gemini 3.1 Pro Preview | Proprietary | 1,521.31 | 1,516.75 | 1,525.87 | 5.42 | 35,033 | coding | 2026-10-15 | |
| 34 | gpt-5.4-high | openai | Proprietary | 1,520.36 | 1,514.53 | 1,526.2 | 8.87 | 17,600 | coding | 2026-10-15 |
| 35 | claude-sonnet-5-high | anthropic | Proprietary | 1,519.75 | 1,513.55 | 1,525.95 | 10.02 | 13,270 | coding | 2026-10-15 |
| 36 | claude-sonnet-4-5-20250929-high-32k | anthropic | Proprietary | 1,518.96 | 1,514.09 | 1,523.82 | 6.17 | 19,950 | coding | 2026-10-15 |
| 37 | gpt-5.5-high | openai | Proprietary | 1,518.77 | 1,513.06 | 1,524.48 | 8.49 | 19,167 | coding | 2026-10-15 |
| 38 | glm-5.3-max | zai | MIT | 1,518.51 | 1,509.88 | 1,527.13 | 19.36 | 5,400 | coding | 2026-10-15 |
| 39 | gpt-6-sol-max | openai | Proprietary | 1,518.17 | 1,506.6 | 1,529.75 | 34.9 | 2,874 | coding | 2026-10-15 |
| 40 | gemini-3.6-flash-high | Proprietary | 1,518.06 | 1,511.26 | 1,524.86 | 12.04 | 10,368 | coding | 2026-10-15 | |
| 41 | Gemini 3.7 Flash (High) | Proprietary | 1,517.99 | 1,510.29 | 1,525.7 | 15.45 | 7,459 | coding | 2026-10-15 | |
| 42 | Gemini 3 Pro | Proprietary | 1,517.24 | 1,510.3 | 1,524.18 | 12.54 | 8,816 | coding | 2026-10-15 | |
| 43 | gpt-5.6-terra-xhigh | openai | Proprietary | 1,516.83 | 1,510.28 | 1,523.37 | 11.16 | 11,499 | coding | 2026-10-15 |
| 44 | kimi-k2.6 | moonshot | Modified MIT | 1,516.03 | 1,509.15 | 1,522.92 | 12.33 | 11,091 | coding | 2026-10-15 |
| 45 | gpt-5.2-chat-latest-20260210 | openai | Proprietary | 1,514.74 | 1,507.95 | 1,521.52 | 11.98 | 9,641 | coding | 2026-10-15 |
| 46 | dola-seed-2.0-pro | bytedance | Proprietary | 1,513.8 | 1,508.42 | 1,519.19 | 7.55 | 22,061 | coding | 2026-10-15 |
| 47 | grok-4.5 | xai | Proprietary | 1,513.69 | 1,507.04 | 1,520.33 | 11.49 | 11,116 | coding | 2026-10-15 |
| 48 | glm-5.2-max | zai | MIT | 1,513.47 | 1,507.27 | 1,519.67 | 10.02 | 13,394 | coding | 2026-10-15 |
| 49 | gpt-5.5-instant | openai | Proprietary | 1,513.4 | 1,505.66 | 1,521.13 | 15.56 | 7,925 | coding | 2026-10-15 |
| 50 | qwen3.5-max-preview | alibaba | Proprietary | 1,513.03 | 1,505.13 | 1,520.94 | 16.26 | 6,365 | coding | 2026-10-15 |
| 51 | mimo-v2.6-flash | xiaomi | MIT | 1,512.93 | 1,500.97 | 1,524.89 | 37.26 | 2,625 | coding | 2026-10-15 |
| 52 | glm-5.1 | zai | MIT | 1,512.4 | 1,506.88 | 1,517.92 | 7.94 | 17,133 | coding | 2026-10-15 |
| 53 | claude-sonnet-4-5-20250929 | anthropic | Proprietary | 1,511.97 | 1,506.95 | 1,517 | 6.56 | 19,782 | coding | 2026-10-15 |
| 54 | qwen3.6-max-preview | alibaba | Proprietary | 1,511.74 | 1,496.59 | 1,526.9 | 59.77 | 1,617 | coding | 2026-10-15 |
| 55 | ernie-5.1 | baidu | Proprietary | 1,511.72 | 1,504.78 | 1,518.67 | 12.55 | 10,908 | coding | 2026-10-15 |
| 56 | gpt-5.4 | openai | Proprietary | 1,511.49 | 1,505.71 | 1,517.28 | 8.72 | 18,932 | coding | 2026-10-15 |
| 57 | claude-opus-4-1-20250805-thinking-16k | anthropic | Proprietary | 1,511.07 | 1,504.64 | 1,517.51 | 10.78 | 9,919 | coding | 2026-10-15 |
| 58 | grok-4.20-beta-0309-reasoning | xai | Proprietary | 1,510.75 | 1,504.99 | 1,516.52 | 8.66 | 18,377 | coding | 2026-10-15 |
| 59 | gpt-5.5 | openai | Proprietary | 1,510.7 | 1,505.08 | 1,516.32 | 8.22 | 20,064 | coding | 2026-10-15 |
| 60 | grok-4.6-high | xai | Proprietary | 1,509.32 | 1,501.63 | 1,517.01 | 15.38 | 7,222 | coding | 2026-10-15 |
| 61 | gemini-3.5-flash-high | Proprietary | 1,508.19 | 1,502.1 | 1,514.28 | 9.66 | 13,847 | coding | 2026-10-15 | |
| 62 | grok-4.20-multi-agent-beta-0309 | xai | Proprietary | 1,508.19 | 1,502.45 | 1,513.93 | 8.58 | 18,016 | coding | 2026-10-15 |
| 63 | Step 5 Preview | stepfun | Proprietary | 1,507.95 | 1,493.76 | 1,522.14 | 52.42 | 1,719 | coding | 2026-10-15 |
| 64 | grok-4.20-beta1 | xai | Proprietary | 1,507.94 | 1,500.4 | 1,515.48 | 14.81 | 7,499 | coding | 2026-10-15 |
| 65 | gpt-6-luna-max | openai | Proprietary | 1,506.43 | 1,499.76 | 1,513.09 | 11.55 | 11,293 | coding | 2026-10-15 |
| 66 | gemini-3.5-flash-medium | Proprietary | 1,506.11 | 1,499.87 | 1,512.34 | 10.12 | 13,614 | coding | 2026-10-15 | |
| 67 | gemini-3-flash | Proprietary | 1,505.61 | 1,497.83 | 1,513.39 | 15.76 | 6,599 | coding | 2026-10-15 | |
| 68 | claude-opus-4-1-20250805 | anthropic | Proprietary | 1,504.67 | 1,499.31 | 1,510.03 | 7.49 | 15,695 | coding | 2026-10-15 |
| 69 | deepseek-v4-pro-high-20260813 | deepseek | MIT | 1,504.63 | 1,493.25 | 1,516.02 | 33.76 | 2,807 | coding | 2026-10-15 |
| 70 | kimi-k2.5-instant | moonshot | Modified MIT | 1,503.91 | 1,490.37 | 1,517.46 | 47.76 | 1,873 | coding | 2026-10-15 |
| 71 | mimo-v2-pro | xiaomi | Proprietary | 1,502.96 | 1,495.35 | 1,510.58 | 15.1 | 7,268 | coding | 2026-10-15 |
| 72 | gemma-4-31b | Apache 2.0 | 1,502.42 | 1,487.34 | 1,517.5 | 59.2 | 1,418 | coding | 2026-10-15 | |
| 73 | kimi-k2.5-thinking | moonshot | Modified MIT | 1,502.05 | 1,496.88 | 1,507.22 | 6.96 | 20,765 | coding | 2026-10-15 |
| 74 | gemini-3.5-flash-lite | Proprietary | 1,501.51 | 1,494.59 | 1,508.42 | 12.46 | 9,924 | coding | 2026-10-15 | |
| 75 | gpt-5.6-luna-xhigh | openai | Proprietary | 1,501.37 | 1,494.72 | 1,508.03 | 11.54 | 11,127 | coding | 2026-10-15 |
| 76 | hy3 | tencent | Apache 2.0 | 1,501.34 | 1,490.88 | 1,511.79 | 28.45 | 3,329 | coding | 2026-10-15 |
| 77 | longcat-flash-chat-2602-exp | meituan | Proprietary | 1,501.11 | 1,493.83 | 1,508.4 | 13.82 | 8,154 | coding | 2026-10-15 |
| 78 | deepseek-v4-pro | deepseek | MIT | 1,500.58 | 1,494.66 | 1,506.51 | 9.13 | 17,136 | coding | 2026-10-15 |
| 79 | qwen3.7-plus | alibaba | Proprietary | 1,500.21 | 1,493.82 | 1,506.59 | 10.61 | 12,183 | coding | 2026-10-15 |
| 80 | grok-4.1-thinking | xai | Proprietary | 1,499.81 | 1,494.27 | 1,505.34 | 7.97 | 15,421 | coding | 2026-10-15 |
| 81 | qwen3.8-27b | alibaba | Apache 2.0 | 1,499.13 | 1,491.03 | 1,507.23 | 17.09 | 6,417 | coding | 2026-10-15 |
| 82 | claude-opus-4-20250514-thinking-16k | anthropic | Proprietary | 1,498.3 | 1,490.49 | 1,506.1 | 15.87 | 6,596 | coding | 2026-10-15 |
| 83 | mistral-large-4 | mistral | Proprietary | 1,498.07 | 1,483.56 | 1,512.59 | 54.83 | 1,685 | coding | 2026-10-15 |
| 84 | glm-5 | zai | MIT | 1,497.73 | 1,490.51 | 1,504.94 | 13.55 | 7,637 | coding | 2026-10-15 |
| 85 | gpt-5.3-chat-latest | openai | Proprietary | 1,497.53 | 1,490.48 | 1,504.58 | 12.94 | 9,180 | coding | 2026-10-15 |
| 86 | grok-4.7-xhigh | xai | Proprietary | 1,497.14 | 1,485.02 | 1,509.27 | 38.29 | 2,522 | coding | 2026-10-15 |
| 87 | minimax-m3 | minimax | MiniMax Community License | 1,496.69 | 1,490.99 | 1,502.39 | 8.45 | 18,242 | coding | 2026-10-15 |
| 88 | qwen3.6-plus | alibaba | Proprietary | 1,495.58 | 1,489.32 | 1,501.84 | 10.21 | 14,688 | coding | 2026-10-15 |
| 89 | gpt-5.4-mini-high | openai | Proprietary | 1,494.61 | 1,488.72 | 1,500.51 | 9.03 | 17,236 | coding | 2026-10-15 |
| 90 | inkling | thinky | Apache 2.0 | 1,493.3 | 1,486.68 | 1,499.92 | 11.4 | 11,078 | coding | 2026-10-15 |
| 91 | grok-4.1 | xai | Proprietary | 1,492.1 | 1,486.59 | 1,497.61 | 7.89 | 16,027 | coding | 2026-10-15 |
| 92 | gpt-5.1-high | openai | Proprietary | 1,491.79 | 1,484.84 | 1,498.74 | 12.57 | 8,411 | coding | 2026-10-15 |
| 93 | qwen3.5-397b-a17b | alibaba | Apache 2.0 | 1,491.4 | 1,486.61 | 1,496.2 | 5.98 | 26,519 | coding | 2026-10-15 |
| 94 | mimo-v2.5 | xiaomi | MIT | 1,490.71 | 1,484.19 | 1,497.23 | 11.06 | 13,656 | coding | 2026-10-15 |
| 95 | gemini-3-flash (thinking-minimal) | Proprietary | 1,489.69 | 1,484.7 | 1,494.67 | 6.46 | 23,982 | coding | 2026-10-15 | |
| 96 | ernie-5.0-0110 | baidu | Proprietary | 1,489.48 | 1,482.88 | 1,496.08 | 11.35 | 8,968 | coding | 2026-10-15 |
| 97 | gpt-5.2-high | openai | Proprietary | 1,488.99 | 1,482.92 | 1,495.07 | 9.6 | 12,245 | coding | 2026-10-15 |
| 98 | mimo-v2-omni | xiaomi | Proprietary | 1,488.55 | 1,479.89 | 1,497.2 | 19.48 | 5,889 | coding | 2026-10-15 |
| 99 | grok-4.3 | xai | Proprietary | 1,488.09 | 1,482.46 | 1,493.72 | 8.26 | 19,950 | coding | 2026-10-15 |
| 100 | deepseek-v4-pro-high-preview | deepseek | MIT | 1,487.96 | 1,481.87 | 1,494.05 | 9.66 | 16,007 | coding | 2026-10-15 |