智能体竞技场
来自 Wikiprompt,自由的提示词百科
社区 Elo 排行榜,每日从 LMArena 对战汇总。先是总榜,然后是分类明细。
最后更新: 2026-10-12 · 52 个模型
| 排名 | 模型 | 机构 | Elo 分数 |
|---|---|---|---|
| 1 | Claude Opus 5.5 (High) | anthropic | |
| 2 | GPT 6 Astra (Max) | openai | |
| 3 | Claude Fable 5.1 (Max) | anthropic | |
| 4 | Claude Sonnet 5.5 (Max) | anthropic | |
| 5 | GPT 6.1 Sol (Max) | openai | |
| 6 | GPT 6 Sol (Max) | openai | |
| 7 | Gemini 4 Argon (High) | ||
| 8 | Claude Fable 5 (High) | anthropic | |
| 9 | Claude Opus 5 (Max) | anthropic | |
| 10 | Claude Opus 5 (High) | anthropic | |
| 11 | Claude Opus 4.8 (High) | anthropic | |
| 12 | GPT 5.6 Sol (xHigh) | openai | |
| 13 | Claude Sonnet 5 (High) | anthropic | |
| 14 | GPT 5.5 (xHigh) | openai | |
| 15 | Muse Spark 1.3 (Max) | meta | |
| 16 | Deepseek V4.1 Flash (Max) | deepseek | |
| 17 | Kimi K3 (Max) | moonshot | |
| 18 | Hy4 preview | tencent | |
| 19 | MiMo V2.6 Pro | xiaomi | |
| 20 | GLM 5.2 (Max) | zai | |
| 21 | Grok 4.7 (xHigh) | xai | |
| 22 | Gemini 3.8 Flash (High) | ||
| 23 | Qwen3.8 Max | alibaba | |
| 24 | GLM 5.3 (Max) | zai | |
| 25 | GPT 6 Luna (Max) | openai | |
| 26 | DeepSeek V4 Pro (High) (0813) | deepseek | |
| 27 | Grok 4.5 | xai | |
| 28 | GPT 5.4 (High) | openai | |
| 29 | Grok 4.6 (xHigh) | xai | |
| 30 | GPT 5.5 | openai | |
| 31 | GPT 5.6 Terra (xHigh) | openai | |
| 32 | MiMo V2.6 Flash | xiaomi | |
| 33 | Step 5 Preview | stepfun | |
| 34 | Qwen3.8 Flash Next | alibaba | |
| 35 | GLM 5.3 Flash | zai | |
| 36 | GPT 5.6 Luna (xHigh) | openai | |
| 37 | Qwen 3.8 27B | alibaba | |
| 38 | Gemini 3.7 Flash (High) | ||
| 39 | Muse Spark 1.2 (xHigh) | meta | |
| 40 | Muse Spark 1.1 | meta | |
| 41 | Hy3 | tencent | |
| 42 | Qwen3.7 Max | alibaba | |
| 43 | mistral-large-4 | mistral | |
| 44 | Minimax M3 | minimax | |
| 45 | Qwen3.7 Plus | alibaba | |
| 46 | Mimo V2.5 Pro | xiaomi | |
| 47 | Gemini 3.6 Flash (High) | ||
| 48 | Gemini 3.1 Pro Preview | ||
| 49 | Inkling Small | thinky | |
| 50 | Inkling | thinky | |
| 51 | Mistral Medium 3.5 | mistral | |
| 52 | Solar Pro 4 | upstage |
参见
数据来源与方法
排行榜汇总自开放的社区评测。Elo 分数、置信区间与投票数来自 LMArena(社区投票的模型对战,以开放数据集发布)。价格与上下文元数据来自 OpenRouter 公开 API。Wikiprompt 每日快照并保留历史,不进行自有评测。