AA-Briefcase
四个工作场景中的文件交付任务,按任务成功、分析质量和呈现质量进行成对比较。
v4.3 · 10 项评测
解释 AA Intelligence Index v4.3 的 10 项评测、原始指标和权重,按版本查看逐模型成绩并保留 v4.1 历史参考,不跨版本混排或合成新总分。
INTELLIGENCE INDEX V4.3
四个工作场景中的文件交付任务,按任务成功、分析质量和呈现质量进行成对比较。
高经济价值、可交付成果导向的真实知识工作任务。
使用 REST API 完成 SaaS 工作流,触发安全约束违规的任务不得分。
在终端中执行真实任务,与 v2.1 的任务集和结果分开比较。
科研场景中的代码生成、执行和数值计算。
知识准确率与幻觉率分别进入指数;独立 Omniscience Index 不直接作为组成分数。
基于长 PDF 回答跨领域问题,保留全通过与任务宏平均通过率的不同口径。
跨长上下文定位、保持和综合关键信息。
覆盖多学科专家级知识与复杂推理。
要求严谨分析与多步骤推理的科学评测。
按版本展示
展示已核实的来源公开数据,按版本查看并保留旧观测。不同版本不混排;估算保留标记,缺失字段不补算。
智能指数仍为 v4.3,带 * 为原站估算值;GDPval-AA v2 与 AA-Briefcase 展示实时 Elo,已核实当前裁判协议的值标为 v4.3.1。指数中的 Elo 贡献在模型加入时冻结,不能用实时 Elo 重算指数。旧裁判协议未区分的值保留为历史参考,Elo 排序时置于末尾且不编号。其余分项以百分数展示;幻觉率越低越好,缺失值为 —。
| # | 模型 | 机构 | 智能指数 | GDPval-AA v2 (Elo) | AA-Briefcase (Elo) | AutomationBench-AA | Terminal-Bench v4.0 | SciCode | AA-LCR v1.1 | AA-Omniscience 准确率 | AA-Omniscience 幻觉率 | GDP.pdf 全通过率 | HLE | CritPt | 权重 | 推理 | 发布日期 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 (max with fallback) | Anthropic | 53.37 | 1,723.58 裁判协议 v4.3.1 | 1,646.09 裁判协议 v4.3.1 | 59.4% | 52% | 63.1% | 85.3% | 67.2% | 72.6% | 26.2% | 59.1% | 29.7% | 闭源 | 是 | 2026-09-01 |
| 2 | Claude Fable 5.1 (xhigh with fallback) | Anthropic | 53.18 | 1,745.29 裁判协议 v4.3.1 | 1,650.01 裁判协议 v4.3.1 | 57.8% | 55.1% | 60.9% | 83% | 66.2% | 70.5% | 26.2% | 58.7% | 31.1% | 闭源 | 是 | 2026-09-01 |
| 3 | GPT-6 Astra (max) | OpenAI | 52.81 | 1,580.2 裁判协议 v4.3.1 | 1,562.01 裁判协议 v4.3.1 | 68.5% | 59.1% | 56.5% | 80.7% | 62.6% | 51.3% | 31% | 54.7% | 31.7% | 闭源 | 是 | 2026-09-03 |
| 4 | GPT-6 Astra (xhigh) | OpenAI | 52.51 | 1,555.23 裁判协议 v4.3.1 | 1,533.73 裁判协议 v4.3.1 | 67.2% | 59.6% | 55.7% | 80% | 61.9% | 48.3% | 32.2% | 54.6% | 31.4% | 闭源 | 是 | 2026-09-03 |
| 5 | Claude Fable 5.1 (high with fallback) | Anthropic | 51.21 | 1,649.77 裁判协议 v4.3.1 | 1,578.19 裁判协议 v4.3.1 | 55.3% | 52% | 58.7% | 83.7% | 64.9% | 68.8% | 26.8% | 55.9% | 30.3% | 闭源 | 是 | 2026-09-01 |
| 6 | GPT-6 Astra (high) | OpenAI | 51.05 | 1,529.7 裁判协议 v4.3.1 | 1,493.87 裁判协议 v4.3.1 | 66.6% | 54% | 55.4% | 80% | 61.1% | 44.8% | 31% | 53.1% | 28.9% | 闭源 | 是 | 2026-09-03 |
| 7 | Claude Opus 5 (max) | Anthropic | 50.7 | 1,735.09 裁判协议 v4.3.1 | 1,633.44 裁判协议 v4.3.1 | 56.6% | 49% | 56.4% | 79.3% | 60.9% | 60.8% | 21.6% | 54.9% | 29.1% | 闭源 | 是 | 2026-07-24 |
| 8 | Claude Fable 5历史 | Anthropic | 49.7 | 1,631.46 裁判协议 v4.3.1 | 1,529.62 裁判协议 v4.3.1 | 54.1% | 42.4% | 61% | 82.3% | 65.3% | 63.6% | 24% | 55.5% | 28.6% | 闭源 | 是 | 2026-06-09 |
| 9 | GPT-6 Astra (medium) | OpenAI | 49.67 | 1,500.67 裁判协议 v4.3.1 | 1,450.6 裁判协议 v4.3.1 | 64.6% | 49.5% | 54.2% | 79.7% | 60.6% | 46.5% | 30.4% | 52.7% | 29.1% | 闭源 | 是 | 2026-09-03 |
| 10 | Claude Opus 5 (xhigh) | Anthropic | 49.65 | 1,708.14 裁判协议 v4.3.1 | 1,624.56 裁判协议 v4.3.1 | 53.2% | 46.5% | 55.7% | 80.3% | 59.5% | 59.5% | 21% | 54.4% | 27.7% | 闭源 | 是 | 2026-07-24 |
| 11 | Claude Fable 5.1 (medium with fallback) | Anthropic | 49.06 | 1,579.31 裁判协议 v4.3.1 | 1,531.2 裁判协议 v4.3.1 | 54.7% | 44.9% | 56.4% | 84.7% | 63.1% | 69.1% | 26.8% | 53.8% | 29.1% | 闭源 | 是 | 2026-09-01 |
| 12 | Claude Opus 5 (high) | Anthropic | 48.24 | 1,628.94 裁判协议 v4.3.1 | 1,556.66 裁判协议 v4.3.1 | 53.6% | 46% | 55.4% | 79% | 58.9% | 61.2% | 19.6% | 52.8% | 28.3% | 闭源 | 是 | 2026-07-24 |
| 13 | Muse Spark 1.3 (max) | Meta | 48.17 | 1,703.34 裁判协议 v4.3.1 | 1,589.18 裁判协议 v4.3.1 | 57.9% | 33.3% | 58.8% | 83% | 43.6% | 32.9% | 26.6% | 48.7% | 24.9% | 闭源 | 是 | 2026-09-02 |
| 14 | GPT-5.6 Sol (max) | OpenAI | 47.06 | 1,586.78 裁判协议 v4.3.1 | 1,463.44 裁判协议 v4.3.1 | 60.1% | 39.9% | 57.1% | 84% | 59.4% | 92.2% | 27.2% | 49.5% | 32.3% | 闭源 | 是 | 2026-07-09 |
| 15 | Claude Fable 5.1 (low with fallback) | Anthropic | 47.04 | 1,503.72 裁判协议 v4.3.1 | 1,483.73 裁判协议 v4.3.1 | 52.2% | 40.4% | 56.7% | 82.3% | 60.2% | 65.6% | 28% | 48.9% | 27.7% | 闭源 | 是 | 2026-09-01 |
| 16 | GPT-6 Astra (low) | OpenAI | 45.99 | 1,419.29 裁判协议 v4.3.1 | 1,253.1 裁判协议 v4.3.1 | 59.1% | 41.9% | 54.1% | 80% | 59.5% | 46.9% | 30.4% | 49.2% | 26.3% | 闭源 | 是 | 2026-09-03 |
| 17 | Qwen3.8 Max (0902) | Alibaba | 45.44 | 1,664.28 裁判协议 v4.3.1 | 1,609.69 裁判协议 v4.3.1 | 56.2% | 38.9% | 52.1% | 80.3% | 31.7% | 28.8% | 22.8% | 43.1% | 17.7% | 闭源 | 是 | 2026-09-02 |
| 18 | GPT-6 Astra (Non-reasoning) 历史参考 2026-09-09 | OpenAI | 45.17 | 1,542.59 历史参考 · 裁判协议未区分 | 1,471.32 历史参考 · 裁判协议未区分 | 61.8% | 50.5% | 53.5% | 70.7% | 55.6% | 65.4% | 26.8% | 37.1% | 19.7% | 闭源 | 否 | 2026-09-03 |
| 19 | Muse Spark 1.3 (xhigh) | Meta | 45.16 | 1,662.34 裁判协议 v4.3.1 | 1,483.22 裁判协议 v4.3.1 | 56.8% | 16.7% | 59.7% | 83% | 41.5% | 31.5% | 24.2% | 47.5% | 26% | 闭源 | 是 | 2026-09-02 |
| 20 | Claude Opus 5 (medium) | Anthropic | 45.06 | 1,524.87 裁判协议 v4.3.1 | 1,439.04 裁判协议 v4.3.1 | 54.3% | 34.3% | 51.5% | 82% | 57.1% | 60.7% | 20% | 51.3% | 26.9% | 闭源 | 是 | 2026-07-24 |
| 21 | GLM-5.3 (max) | Z AI | 44.86 | 1,633.8 裁判协议 v4.3.1 | 1,504.38 裁判协议 v4.3.1 | 62.2% | 41.9% | 59% | 79.7% | 33.9% | 29.6% | 11.2% | 42.3% | 19.1% | 开放 | 是 | 2026-08-18 |
| 22 | Grok 4.6 (high) | SpaceXAI | 44.41 | 1,642.96 裁判协议 v4.3.1 | 1,534.13 裁判协议 v4.3.1 | 66.7% | 21.2% | 56.5% | 80.3% | 48.2% | 34.3% | 17% | 42.9% | 17.1% | 闭源 | 是 | 2026-08-12 |
| 23 | Grok 4.6 (xhigh) | SpaceXAI | 44.27 | 1,663.07 裁判协议 v4.3.1 | 1,545.11 裁判协议 v4.3.1 | 67% | 17.2% | 53% | 81% | 43% | 24% | 17.2% | 44.1% | 19.7% | 闭源 | 是 | 2026-08-12 |
| 24 | GPT-5.6 Sol (xhigh) | OpenAI | 44.14 | 1,584.88 裁判协议 v4.3.1 | 1,434.68 裁判协议 v4.3.1 | 55.3% | 24.7% | 57.1% | 82.3% | 58.8% | 91.9% | 27.6% | 47.3% | 28.6% | 闭源 | 是 | 2026-07-09 |
| 25 | Kimi K3 (max) | Kimi | 43.78 | 1,547.63 裁判协议 v4.3.1 | 1,488.1 裁判协议 v4.3.1 | 58.3% | 12.6% | 59.5% | 88.7% | 47.6% | 53.2% | 22% | 46.9% | 23.4% | 开放 | 是 | 2026-07-16 |
| 26 | Grok 4.6 (medium) | SpaceXAI | 43.01 | 1,642.56 裁判协议 v4.3.1 | 1,490.6 裁判协议 v4.3.1 | 63.2% | 13.1% | 55.9% | 81% | 41.9% | 24% | 17.8% | 42.1% | 17.7% | 闭源 | 是 | 2026-08-12 |
| 27 | GPT-5.6 Sol (high) | OpenAI | 42.5 | 1,524.01 裁判协议 v4.3.1 | 1,360.88 裁判协议 v4.3.1 | 55.3% | 20.7% | 57.8% | 81.7% | 58.4% | 91.2% | 27.8% | 46% | 25.7% | 闭源 | 是 | 2026-07-09 |
| 28 | GPT-5.6 Terra (max) | OpenAI | 42.25 | 1,476.96 裁判协议 v4.3.1 | 1,330 裁判协议 v4.3.1 | 59.6% | 35.4% | 55% | 83% | 46.8% | 87.9% | 24% | 42.9% | 30% | 闭源 | 是 | 2026-07-09 |
| 29 | Claude Opus 4.8 (max)历史 | Anthropic | 41.99 | 1,489.04 裁判协议 v4.3.1 | 1,315.95 裁判协议 v4.3.1 | 45.6% | 21.7% | 54.4% | 77.7% | 48.8% | 39.3% | 22.8% | 48.7% | 20.9% | 闭源 | 是 | 2026-05-28 |
| 30 | GLM-5.3-Flash | Z AI | 41.91 | 1,654.95 裁判协议 v4.3.1 | 1,448.95 裁判协议 v4.3.1 | 60.4% | 32.8% | 51.6% | 80% | 27.5% | 27.6% | 15.4% | 39.9% | 15.4% | 开放 | 是 | 2026-08-26 |
| 31 | Gemini 3.8 Flash (high) | 41.19 | 1,463.81 裁判协议 v4.3.1 | 1,201.59 裁判协议 v4.3.1 | 59.9% | 19.7% | 56.6% | 81.3% | 54.6% | 55.2% | 21% | 47.8% | 18.3% | 闭源 | 是 | 2026-09-02 | |
| 32 | Claude Opus 4.7 (max)历史 | Anthropic | 40.69* | 1,395.78 裁判协议 v4.3.1 | 1,251.5 裁判协议 v4.3.1 | — | — | — | 78.7% | 48.9% | 42.3% | — | 42.3% | 12% | 闭源 | 是 | 2026-04-16 |
| 33 | Qwen3.8 Max历史 | Alibaba | 40.3 | 1,630.39 裁判协议 v4.3.1 | 1,387.89 裁判协议 v4.3.1 | 49.2% | 18.7% | 53.2% | 78.3% | 31.9% | 41.7% | 20.2% | 43% | 20% | 闭源 | 是 | 2026-08-03 |
| 34 | Qwen3.8 2.4T A95B | Alibaba | 40.04 | 1,627.82 裁判协议 v4.3.1 | 1,438.5 裁判协议 v4.3.1 | 57.2% | 11.1% | 54.1% | 80.3% | 31.3% | 39.2% | 15.6% | 42.4% | 20% | 开放 | 是 | 2026-08-12 |
| 35 | Gemini 3.8 Flash (medium) | 40 | 1,455.38 裁判协议 v4.3.1 | 1,176.54 裁判协议 v4.3.1 | 60.9% | 19.7% | 55.1% | 84% | 53% | 51.9% | 22.8% | 42.1% | 12.3% | 闭源 | 是 | 2026-09-02 | |
| 36 | Qwen3.8-Flash-Next | Alibaba | 39.91 | 1,647.02 裁判协议 v4.3.1 | 1,586.58 裁判协议 v4.3.1 | 55.9% | 25.3% | 50.6% | 79.7% | 24.5% | 45.3% | 15.6% | 38% | 11.1% | 开放 | 是 | 2026-08-26 |
| 37 | Muse Spark 1.2 (xhigh)历史 | Meta | 39.8 | 1,523.32 裁判协议 v4.3.1 | 1,343.5 裁判协议 v4.3.1 | 40.6% | 7.1% | 57.4% | 79% | 45.4% | 33.3% | 17.4% | 45.5% | 17.7% | 闭源 | 是 | 2026-08-05 |
| 38 | Claude Opus 5 (low) | Anthropic | 39.79 | 1,371.52 裁判协议 v4.3.1 | 1,215.73 裁判协议 v4.3.1 | 51.8% | 26.3% | 49.2% | 81.3% | 56% | 62.2% | 17.2% | 43.4% | 23.1% | 闭源 | 是 | 2026-07-24 |
| 39 | Gemini 3.7 Flash (medium)历史 | 39.62* | 1,406.6 裁判协议 v4.3.1 | — | — | — | 59.8% | 83% | 54% | 65.9% | — | 39% | 9.4% | 闭源 | 是 | 2026-08-13 | |
| 40 | DeepSeek V4.1 Flash (max) | DeepSeek | 39.55 | 1,632.06 裁判协议 v4.3.1 | 1,423.72 裁判协议 v4.3.1 | 68.9% | 26.8% | 51.9% | 84% | 46.4% | 96.5% | 12.8% | 39.2% | 14.3% | 开放 | 是 | 2026-09-10 |
| 41 | GPT-5.6 Sol (medium) | OpenAI | 39.48 | 1,426.5 裁判协议 v4.3.1 | 1,236.71 裁判协议 v4.3.1 | 51.3% | 14.6% | 57.4% | 80.3% | 57.8% | 90.8% | 26.2% | 42.2% | 22.9% | 闭源 | 是 | 2026-07-09 |
| 42 | Gemini 3.7 Flash (high)历史 | 39.43 | 1,433.14 裁判协议 v4.3.1 | 1,115.67 裁判协议 v4.3.1 | 62% | 13.6% | 57.2% | 81.7% | 55.3% | 64.5% | 23.6% | 47.9% | 14.3% | 闭源 | 是 | 2026-08-13 | |
| 43 | Grok 4.5 (high)历史 | SpaceXAI | 39.08 | 1,429.6 裁判协议 v4.3.1 | 1,283.38 裁判协议 v4.3.1 | 57.9% | 10.6% | 55% | 79.3% | 51.5% | 54.1% | 18.8% | 42.7% | 15.4% | 闭源 | 是 | 2026-07-08 |
| 44 | GPT-5.4 (xhigh)历史 | OpenAI | 38.98* | 1,306.71 裁判协议 v4.3.1 | — | — | — | — | 82% | 50.8% | 91.7% | — | 43.7% | 23.4% | 闭源 | 是 | 2026-03-05 |
| 45 | GPT-5.5 (xhigh)历史 | OpenAI | 38.63 | 1,395.85 裁判协议 v4.3.1 | 1,135.79 裁判协议 v4.3.1 | 47.3% | 14.6% | 55.8% | 84.3% | 58% | 89% | 21.2% | 45.8% | 27.1% | 闭源 | 是 | 2026-04-23 |
| 46 | Claude Sonnet 5 (max) | Anthropic | 38.36 | 1,500.86 裁判协议 v4.3.1 | 1,355.19 裁判协议 v4.3.1 | 36.5% | 14.1% | 54.3% | 82% | 40.1% | 39.4% | 13.2% | 41.3% | 16.9% | 闭源 | 是 | 2026-06-30 |
| 47 | GPT-5.6 Terra (xhigh) | OpenAI | 38.19 | 1,478.6 裁判协议 v4.3.1 | 1,337.28 裁判协议 v4.3.1 | 47.1% | 10.1% | 52.3% | 79% | 45.5% | 89% | 24.6% | 41.9% | 27.1% | 闭源 | 是 | 2026-07-09 |
| 48 | GPT-5.6 Luna (max) | OpenAI | 37.5 | 1,455.6 裁判协议 v4.3.1 | 1,332.9 裁判协议 v4.3.1 | 50.2% | 11.6% | 53.6% | 83.7% | 42.7% | 92.6% | 24% | 39.5% | 20.6% | 闭源 | 是 | 2026-07-09 |
| 49 | GPT-5.5 (high)历史 | OpenAI | 37.29 | 1,371.51 裁判协议 v4.3.1 | 1,088.84 裁判协议 v4.3.1 | 44.3% | 9.1% | 56.1% | 84.3% | 57% | 89.1% | 22.6% | 45% | 25.4% | 闭源 | 是 | 2026-04-23 |
| 50 | Gemini 3.7 Flash (low)历史 | 36.95* | 1,354.06 裁判协议 v4.3.1 | — | — | — | 55.7% | 78.7% | 53.6% | 67.7% | — | 35.1% | 5.7% | 闭源 | 是 | 2026-08-13 | |
| 51 | DeepSeek V4 Pro 0813 (max) | DeepSeek | 36.28 | 1,493.31 裁判协议 v4.3.1 | 1,264.67 裁判协议 v4.3.1 | 56.7% | 14.1% | 51% | 80.3% | 49.1% | 94.8% | 11.4% | 41% | 18% | 开放 | 是 | 2026-08-13 |
| 52 | Agnes 3.0 Flash | Sapiens AI | 35.5* | 1,573.47 裁判协议 v4.3.1 | — | 50.7% | 7.1% | 51.6% | 81% | 25.5% | 48.4% | 10% | 38.5% | 15.1% | 闭源 | 是 | 2026-09-11 |
| 53 | Grok 4.6 (low) | SpaceXAI | 35.41 | 1,461.3 裁判协议 v4.3.1 | 1,293.13 裁判协议 v4.3.1 | 53.4% | 3% | 49.4% | 80.7% | 43.3% | 30.6% | 15.8% | 27.6% | 5.7% | 闭源 | 是 | 2026-08-12 |
| 54 | Agnes 2.5 Pro Beta | Sapiens AI | 35.24* | 1,375.77 裁判协议 v4.3.1 | — | — | — | 48.8% | 83% | 16.8% | 32.8% | — | 37.5% | 15.7% | 闭源 | 是 | 2026-08-26 |
| 55 | DeepSeek V4 Flash Vision (max) | DeepSeek | 35.01 | 1,577.21 裁判协议 v4.3.1 | 1,432.36 裁判协议 v4.3.1 | 47.5% | 12.1% | 49.7% | 81.3% | 38.6% | 91.5% | 12% | 34.5% | 10.9% | 闭源 | 是 | 2026-08-21 |
| 56 | GPT-5.6 Luna (xhigh) | OpenAI | 34.77 | 1,428.47 裁判协议 v4.3.1 | 1,268.01 裁判协议 v4.3.1 | 42.6% | 3.5% | 50.5% | 81.7% | 42.4% | 92.5% | 23.8% | 37% | 20.6% | 闭源 | 是 | 2026-07-09 |
| 57 | Claude Sonnet 5 (xhigh) | Anthropic | 34.71 | 1,400.77 裁判协议 v4.3.1 | 1,273.41 裁判协议 v4.3.1 | 34.5% | 7.1% | 54.1% | 76.7% | 39% | 58.6% | 12.6% | 39% | 15.4% | 闭源 | 是 | 2026-06-30 |
| 58 | DeepSeek V4 Flash 0731 (max)历史 | DeepSeek | 34.53 | 1,441.89 裁判协议 v4.3.1 | 1,253.08 裁判协议 v4.3.1 | 54% | 12.1% | 50.3% | 79.7% | 40.4% | 91.7% | 11% | 38.6% | 16.6% | 开放 | 是 | 2026-07-31 |
| 59 | GPT-5.6 Terra (high) | OpenAI | 34.49 | 1,415.36 裁判协议 v4.3.1 | 1,201.36 裁判协议 v4.3.1 | 42% | 1.5% | 52.4% | 77.7% | 45.5% | 89.8% | 20.8% | 38.5% | 22.9% | 闭源 | 是 | 2026-07-09 |
| 60 | Gemini 3.6 Flash历史 | 34.34 | 1,331.37 裁判协议 v4.3.1 | 952.75 裁判协议 v4.3.1 | 53% | 7.1% | 53.4% | 80% | 50% | 55.6% | 17.4% | 40.8% | 10.6% | 闭源 | 是 | 2026-07-21 | |
| 61 | Muse Spark 1.1 (xhigh)历史 | Meta | 34.27 | 1,294.15 裁判协议 v4.3.1 | 860.36 裁判协议 v4.3.1 | 38.8% | 6.1% | 58.8% | 77.7% | 52% | 50% | 14.4% | 46.2% | 15.1% | 闭源 | 是 | 2026-07-09 |
| 62 | GPT-5.5 (medium)历史 | OpenAI | 34.15 | 1,288.18 裁判协议 v4.3.1 | 1,000 裁判协议 v4.3.1 | 40.1% | 5.1% | 54.5% | 83% | 56.8% | 89.6% | 20.6% | 42.4% | 18.6% | 闭源 | 是 | 2026-04-23 |
| 63 | GLM-5.2 (max)历史 | Z AI | 34.01 | 1,406.07 裁判协议 v4.3.1 | 1,231.38 裁判协议 v4.3.1 | 28.4% | 1% | 51.2% | 78.3% | 24.3% | 26.3% | 10.4% | 41.1% | 20.9% | 开放 | 是 | 2026-06-16 |
| 64 | Qwen3.8 27B (xhigh) | Alibaba | 33.9 | 1,463.25 裁判协议 v4.3.1 | 1,397.82 裁判协议 v4.3.1 | 48.2% | 5.6% | 46.6% | 82% | 15.6% | 30.3% | 16.4% | 33.9% | 5.4% | 开放 | 是 | 2026-08-14 |
| 65 | GPT-5.6 Sol (low) | OpenAI | 33.8 | 1,354.85 裁判协议 v4.3.1 | 1,042.06 裁判协议 v4.3.1 | 41% | 1% | 56.4% | 78% | 57.2% | 89.4% | 21% | 39.4% | 14.9% | 闭源 | 是 | 2026-07-09 |
| 66 | Gemini 3.8 Flash (low) | 33.79 | 1,358.55 裁判协议 v4.3.1 | 1,055.59 裁判协议 v4.3.1 | 36.5% | 10.1% | 55% | 80.7% | 52.2% | 64.6% | 18.6% | 37.1% | 4% | 闭源 | 是 | 2026-09-02 | |
| 67 | Gemini 3.5 Flash (medium)历史 | 33.63* | — | 870.71 裁判协议 v4.3.1 | — | — | — | 74.3% | 51% | 61.8% | — | 41.3% | 10.9% | 闭源 | 是 | 2026-05-19 | |
| 68 | Motif 3 | Motif Technologies | 33.57* | 1,198.83 裁判协议 v4.3.1 | — | — | — | 42.2% | 76% | 30.1% | 28.4% | — | 37% | 6.6% | 开放 | 是 | 2026-08-12 |
| 69 | Gemini 3.5 Flash历史 | 32.98 | 1,259.06 裁判协议 v4.3.1 | 869.74 裁判协议 v4.3.1 | 42.1% | 6.6% | 53.9% | 73.3% | 51.4% | 62.2% | 19.8% | 42.7% | 13.1% | 闭源 | 是 | 2026-05-19 | |
| 70 | GPT-5.3 Codex (xhigh) | OpenAI | 32.5* | — | 865.74 裁判协议 v4.3.1 | — | — | — | 83.3% | 52.9% | 89.2% | — | 42.5% | 16.9% | 闭源 | 是 | 2026-02-05 |
| 71 | GPT-5.6 Luna (high) | OpenAI | 32.41 | 1,375.25 裁判协议 v4.3.1 | 1,173.05 裁判协议 v4.3.1 | 35.6% | 2.5% | 51.6% | 80.3% | 41.8% | 92.4% | 22.2% | 33.4% | 16.6% | 闭源 | 是 | 2026-07-09 |
| 72 | Motif 3 (Beta) | Motif Technologies | 32.31* | 1,182.62 裁判协议 v4.3.1 | — | — | — | — | 74.7% | 21% | 49.1% | — | 40.4% | 6% | 闭源 | 是 | 2026-07-14 |
| 73 | Claude Sonnet 5 (high) | Anthropic | 32.03 | 1,308.45 裁判协议 v4.3.1 | 1,177.84 裁判协议 v4.3.1 | 32.1% | 5.1% | 54.3% | 76.7% | 37.4% | 65.7% | 9.4% | 35.7% | 15.1% | 闭源 | 是 | 2026-06-30 |
| 74 | Claude Opus 4.6 (max)历史 | Anthropic | 31.95* | — | — | — | — | — | 78% | 47% | 62.8% | — | 39.9% | 12.6% | 闭源 | 是 | 2026-02-05 |
| 75 | Muse Spark历史 | Meta | 31.3* | 1,076.31 裁判协议 v4.3.1 | 644.1 裁判协议 v4.3.1 | — | — | — | 78% | 49.6% | 84.2% | — | 40.7% | 11.3% | 闭源 | 是 | 2026-04-08 |
| 76 | Claude Opus 4.7 (Non-reasoning, high)历史 | Anthropic | 30.93* | — | 1,071.03 裁判协议 v4.3.1 | — | — | — | 75.7% | 44.7% | 54.1% | — | 33.3% | 5.1% | 闭源 | 否 | 2026-04-16 |
| 77 | DeepSeek V4 Pro (max)历史 | DeepSeek | 30.87 | 1,223.37 裁判协议 v4.3.1 | 924.56 裁判协议 v4.3.1 | 56.3% | 14.6% | 50.8% | 74.7% | 43% | 94.1% | 13.4% | 37.5% | 12.9% | 开放 | 是 | 2026-04-24 |
| 78 | K2 Horizon 375B A23B | Institute of Foundation Models | 30.79 | 1,400 裁判协议 v4.3.1 | 1,298.34 裁判协议 v4.3.1 | 37.2% | 1.5% | 42.9% | 80% | 18.2% | 25.9% | 7.4% | 32% | 4.6% | 开放 | 是 | 2026-09-03 |
| 79 | GPT-5.5 (low)历史 | OpenAI | 30.71* | 1,112.71 裁判协议 v4.3.1 | — | — | — | — | 81% | 54.9% | 88% | — | 32.7% | 8% | 闭源 | 是 | 2026-04-23 |
| 80 | Kimi K3 (low) | Kimi | 30.48 | 1,185.27 裁判协议 v4.3.1 | 984.78 裁判协议 v4.3.1 | 49.3% | 12.6% | 52.7% | 79.3% | 45.8% | 77.1% | 18.6% | 25% | 3.1% | 开放 | 是 | 2026-07-16 |
| 81 | Claude Sonnet 4.6 (max)历史 | Anthropic | 30.45 | 1,295.41 裁判协议 v4.3.1 | 1,065.11 裁判协议 v4.3.1 | 20.1% | 3% | 50.1% | 80% | 40.9% | 48.4% | 15.8% | 33.6% | 3.1% | 闭源 | 是 | 2026-02-17 |
| 82 | GPT-5.2 (xhigh)历史 | OpenAI | 30.45* | — | — | — | — | — | 82.7% | 44.3% | 81.2% | — | 37.7% | 11.6% | 闭源 | 是 | 2025-12-11 |
| 83 | GPT-5.6 Terra (medium) | OpenAI | 30.42 | 1,318.34 裁判协议 v4.3.1 | 1,040.72 裁判协议 v4.3.1 | 33.5% | 1% | 50.5% | 74% | 44.6% | 89.8% | 17% | 33.3% | 17.4% | 闭源 | 是 | 2026-07-09 |
| 84 | Apodex 1.1 | Apodex | 30.37* | 1,273.14 裁判协议 v4.3.1 | — | — | — | 45.5% | 79.3% | 31.7% | 78.4% | — | 34.1% | 4.6% | 闭源 | 是 | 2026-08-30 |
| 85 | Gemini 3.1 Pro Preview | 30.36 | 903.94 裁判协议 v4.3.1 | 458.83 裁判协议 v4.3.1 | 35.4% | 4% | 58.7% | 82% | 54.9% | 50.9% | 17.8% | 47% | 17.7% | 闭源 | 是 | 2026-02-19 | |
| 86 | DeepSeek V4 Pro (high)历史 | DeepSeek | 30.11* | 1,218.72 裁判协议 v4.3.1 | — | — | — | — | 70.3% | 41.4% | 88.7% | — | 35.2% | 10% | 开放 | 是 | 2026-04-24 |
| 87 | Qwen3.7 Max历史 | Alibaba | 29.87 | 1,189.86 裁判协议 v4.3.1 | 917.94 裁判协议 v4.3.1 | 23% | 1.5% | 49.5% | 79% | 31.1% | 25.6% | 8.6% | 40.5% | 13.4% | 闭源 | 是 | 2026-05-19 |
| 88 | MiniMax-M3 | MiniMax | 29.61 | 1,303.96 裁判协议 v4.3.1 | 1,096.03 裁判协议 v4.3.1 | 21.3% | 2% | 47.1% | 83% | 16.7% | 18.4% | 9.8% | 39% | 3.7% | 开放 | 是 | 2026-06-01 |
| 89 | Claude Opus 4.5历史 | Anthropic | 29.1* | — | — | — | — | — | 77.3% | 46.6% | 61% | — | 30.1% | 4.6% | 闭源 | 是 | 2025-11-24 |
| 90 | Claude Sonnet 5 (Non-reasoning) | Anthropic | 28.94* | 1,283.47 裁判协议 v4.3.1 | — | — | — | — | 70% | 33.8% | 52% | — | 19% | 1.1% | 闭源 | 否 | 2026-06-30 |
| 91 | MiMo-V2-Pro历史 | Xiaomi | 28.64* | — | — | — | — | — | 68.3% | 26.6% | 30% | — | 30.4% | 0.3% | 闭源 | 是 | 2026-03-18 |
| 92 | GPT-5.2 Codex (xhigh)历史 | OpenAI | 28.5* | — | — | — | — | — | 82.3% | 41.1% | 73.4% | — | 35.7% | 8.7% | 闭源 | 是 | 2025-12-11 |
| 93 | Claude Sonnet 5 (medium) | Anthropic | 28.44 | 1,222.52 裁判协议 v4.3.1 | 1,053.88 裁判协议 v4.3.1 | 27.9% | 2% | 51.6% | 73.7% | 37.1% | 69.9% | 11.6% | 30% | 8.6% | 闭源 | 是 | 2026-06-30 |
| 94 | Qwen3.6 Max Preview历史 | Alibaba | 28.37* | — | — | — | — | — | 80.7% | 37.9% | 46.2% | — | 30.8% | 3.7% | 闭源 | 是 | 2026-04-20 |
| 95 | GPT-5.6 Sol (Non-reasoning) | OpenAI | 28.33* | 1,273.32 裁判协议 v4.3.1 | 1,015.25 裁判协议 v4.3.1 | 22.7% | — | 47.7% | 62.3% | 48.7% | 92.8% | 15.2% | 16.7% | 5.1% | 闭源 | 否 | 2026-07-09 |
| 96 | Nex-N2-Pro | Nex AGI | 28.2* | 1,175.2 裁判协议 v4.3.1 | — | 17.6% | — | 43.3% | 81.7% | 34.8% | 94.9% | 12.6% | 33.7% | 8.6% | 开放 | 是 | 2026-06-02 |
| 97 | Solar Pro 4 | Upstage | 28.15* | 1,172.77 裁判协议 v4.3.1 | — | 9.1% | 0.5% | 44.6% | 74% | 18.9% | 24.4% | 5.6% | 29.2% | 5.4% | 闭源 | 是 | 2026-08-06 |
| 98 | Gemini 3 Pro Preview (high)历史 | 27.96* | — | — | — | — | — | 76% | 55.8% | 91.5% | — | 39.7% | 9.1% | 闭源 | 是 | 2025-11-18 | |
| 99 | GPT-5.6 Terra (low) | OpenAI | 27.92 | 1,177.99 裁判协议 v4.3.1 | 1,014.49 裁判协议 v4.3.1 | 29.1% | 1.5% | 49.9% | 71.3% | 43.7% | 89.9% | 17.6% | 29.2% | 9.4% | 闭源 | 是 | 2026-07-09 |
| 100 | GLM-5历史 | Z AI | 27.91* | — | — | — | — | — | 75.7% | 26.3% | 35.3% | — | 29.3% | 2% | 开放 | 是 | 2026-02-11 |
| 101 | Qwen3.8 27B (medium) | Alibaba | 27.81 | 1,430.39 裁判协议 v4.3.1 | 1,375.7 裁判协议 v4.3.1 | 40.3% | 5.1% | 39% | 79.7% | 18.4% | 66.7% | 12.8% | 14.1% | 0% | 开放 | 是 | 2026-08-14 |
| 102 | Agnes 2.5 Pro Alpha | Sapiens AI | 27.8 | 1,087.81 裁判协议 v4.3.1 | 1,195.25 裁判协议 v4.3.1 | 38.4% | 3% | 42.9% | 75.7% | 33.5% | 88.1% | 9% | 33.6% | 10.9% | 开放 | 是 | 2026-07-24 |
| 103 | GPT-5.4 (low)历史 | OpenAI | 27.58* | — | — | — | — | — | 76.7% | 47.9% | 82.6% | — | 30.8% | 7.4% | 闭源 | 是 | 2026-03-05 |
| 104 | Kimi K2.6历史 | Kimi | 27.46 | 1,096.33 裁判协议 v4.3.1 | 823.87 裁判协议 v4.3.1 | 13% | 0.5% | 51.5% | 81% | 32.6% | 40.5% | 13% | 37.5% | 8% | 开放 | 是 | 2026-04-20 |
| 105 | JT-4.1 Flash 236B A21B | China Mobile | 27.29* | 1,193.3 裁判协议 v4.3.1 | — | — | — | — | 71.3% | 24.3% | 43.7% | — | 17.8% | 0% | 闭源 | 否 | 2026-07-09 |
| 106 | Grok Build 0.1 0616历史 | SpaceXAI | 27.17* | 1,138.29 裁判协议 v4.3.1 | — | — | — | — | 74.7% | 51.5% | 93.1% | — | 38.3% | 9.1% | 闭源 | 是 | 2026-06-16 |
| 107 | Quasar 438B (max) | Multiverse Computing | 27.13 | 1,239.08 裁判协议 v4.3.1 | 1,123.48 裁判协议 v4.3.1 | 23.9% | 1% | 48.1% | 76.3% | 15.5% | 21.4% | 5.4% | 18.7% | 9.4% | 闭源 | 是 | 2026-08-10 |
| 108 | Qwen3.6 Plus历史 | Alibaba | 27.01* | 1,065.83 裁判协议 v4.3.1 | — | — | — | — | 78.3% | 26.4% | 34.6% | — | 27.8% | 2.9% | 闭源 | 是 | 2026-04-02 |
| 109 | GPT-5.5 Instant (June 2026) | OpenAI | 26.8 | 661.83 裁判协议 v4.3.1 | 1,081.76 裁判协议 v4.3.1 | 36.4% | 12.6% | 52.5% | 70% | 44.4% | 73.3% | 20.2% | 19.9% | 0% | 闭源 | 是 | 2026-06-25 |
| 110 | GLM-5-Turbo历史 | Z AI | 26.6* | — | — | — | — | — | 71.7% | 28.4% | 62.6% | — | 27.8% | 0.3% | 闭源 | 是 | 2026-03-15 |
| 111 | GPT-5.2 (medium)历史 | OpenAI | 26.5* | — | — | — | — | — | 70.3% | 38.3% | 61.6% | — | 26.7% | 7.9% | 闭源 | 是 | 2025-12-11 |
| 112 | Qwen3.8 27B (low) | Alibaba | 26.49 | 1,402.54 裁判协议 v4.3.1 | 1,277.44 裁判协议 v4.3.1 | 30.1% | 2.5% | 40% | 77.3% | 17.1% | 52.9% | 10.4% | 14% | 0% | 开放 | 是 | 2026-08-14 |
| 113 | GLM-5.1历史 | Z AI | 26.45 | 1,180.01 裁判协议 v4.3.1 | 964.01 裁判协议 v4.3.1 | 20.3% | 2% | 44.8% | 73.7% | 23.7% | 29.9% | 8.4% | 30.1% | 4.6% | 开放 | 是 | 2026-04-07 |
| 114 | MiMo-V2.5-Pro | Xiaomi | 26.41 | 1,186.32 裁判协议 v4.3.1 | 883.43 裁判协议 v4.3.1 | 13.7% | 0% | 50.6% | 79.7% | 22.4% | 24.7% | 4% | 35.7% | 4% | 开放 | 是 | 2026-04-22 |
| 115 | Claude Opus 4.6 (Non-reasoning, high)历史 | Anthropic | 26.35* | — | — | — | — | — | 67% | 45.8% | 80.1% | — | 19.1% | 2.8% | 闭源 | 否 | 2026-02-05 |
| 116 | Gemini 3 Flash历史 | 26.33* | — | — | — | — | — | 78% | 53.4% | 93% | — | 36.6% | 8.6% | 闭源 | 是 | 2025-12-17 | |
| 117 | Kimi K2.7 Code | Kimi | 26.27 | 1,114.49 裁判协议 v4.3.1 | 855.7 裁判协议 v4.3.1 | 24.5% | 1% | 47.8% | 79.3% | 39.6% | 82.4% | 11.2% | 35% | 10% | 开放 | 是 | 2026-06-12 |
| 118 | Inkling Small | Thinking Machines | 26.09 | 1,191.44 裁判协议 v4.3.1 | 912.02 裁判协议 v4.3.1 | 4.8% | 1% | 49.7% | 75.7% | 33.2% | 63% | 11.2% | 33.3% | 8.3% | 开放 | 是 | 2026-07-30 |
| 119 | Qwen3.7 Plus | Alibaba | 25.82 | 885.83 裁判协议 v4.3.1 | 912.73 裁判协议 v4.3.1 | 17.4% | 1% | 46.1% | 73% | 22.5% | 27.7% | 12.2% | 35.6% | 9.1% | 闭源 | 是 | 2026-06-01 |
| 120 | Hy3 | Tencent | 25.77 | 1,135.96 裁判协议 v4.3.1 | 949.65 裁判协议 v4.3.1 | 18.4% | 0.5% | 48.6% | 79% | 32% | 74.1% | 11.2% | 33.5% | 4.9% | 开放 | 是 | 2026-07-06 |
| 121 | K2 Horizon MoVA 36B A4B | Institute of Foundation Models | 25.67 | 1,243.11 裁判协议 v4.3.1 | 1,170.41 裁判协议 v4.3.1 | 26.1% | 0% | 40% | 71.7% | 15% | 30.5% | 4.2% | 23.4% | 2.3% | 开放 | 是 | 2026-09-03 |
| 122 | Grok 4.20 0309 v2历史 | SpaceXAI | 25.66* | — | — | — | — | — | 69% | 27.5% | 17.4% | — | 34.5% | 6.6% | 闭源 | 是 | 2026-04-07 |
| 123 | Inkling | Thinking Machines | 25.54 | 1,165.19 裁判协议 v4.3.1 | 835.63 裁判协议 v4.3.1 | 5% | 1% | 47% | 77.3% | 41.5% | 67.7% | 12.8% | 31.9% | 5.4% | 开放 | 是 | 2026-07-15 |
| 124 | GPT-5.6 Luna (medium) | OpenAI | 25.48 | 1,164.13 裁判协议 v4.3.1 | 934.87 裁判协议 v4.3.1 | 23.1% | 0.5% | 46.8% | 75% | 40.7% | 90.9% | 15.2% | 25.8% | 4.9% | 闭源 | 是 | 2026-07-09 |
| 125 | Grok 4.3 (high)历史 | SpaceXAI | 25.39 | 1,018.49 裁判协议 v4.3.1 | 761.59 裁判协议 v4.3.1 | 1.4% | 0% | 48.3% | 73% | 34.8% | 25.8% | 5.8% | 37.2% | 8% | 闭源 | 是 | 2026-04-30 |
| 126 | Grok 4.20 0309历史 | SpaceXAI | 25.22* | — | — | — | — | — | 67.7% | 28.9% | 22.4% | — | 32.4% | 6% | 闭源 | 是 | 2026-03-10 |
| 127 | MiMo-V2-Omni-0327历史 | Xiaomi | 25.12* | — | — | — | — | — | 73.3% | 17.8% | 40.1% | — | 22.6% | 0.9% | 闭源 | 是 | 2026-03-27 |
| 128 | Ling-3.0-flash-VL | InclusionAI | 24.97 | 1,224.84 裁判协议 v4.3.1 | 985.98 裁判协议 v4.3.1 | 15.7% | 0% | 44.2% | 78.3% | 14.3% | 22% | 8.4% | 22% | 2% | 开放 | 是 | 2026-09-10 |
| 129 | GPT-5 Codex (high)历史 | OpenAI | 24.88* | — | — | — | — | — | 71.7% | 38.7% | 75.4% | — | 27.8% | 5.1% | 闭源 | 是 | 2025-09-23 |
| 130 | DeepSeek V4 Flash (high)历史 | DeepSeek | 24.84 | 1,082.61 裁判协议 v4.3.1 | 1,052.09 裁判协议 v4.3.1 | 28.5% | 3% | 40.2% | 72% | 34.9% | 89% | 10.4% | 30.3% | 3.4% | 开放 | 是 | 2026-04-24 |
| 131 | Grok 4.3 (medium)历史 | SpaceXAI | 24.78* | — | — | — | — | — | 75% | 28.8% | 16.9% | — | 30% | 4.9% | 闭源 | 是 | 2026-04-30 |
| 132 | Claude Sonnet 5 (low) | Anthropic | 24.74 | 1,145.04 裁判协议 v4.3.1 | 927.41 裁判协议 v4.3.1 | 19.9% | 2.5% | 50.1% | 67.3% | 37.4% | 72.8% | 9.4% | 21.9% | 4.6% | 闭源 | 是 | 2026-06-30 |
| 133 | Solar Open2 250B | Upstage | 24.74* | 1,052.82 裁判协议 v4.3.1 | — | — | — | 48% | 71.7% | 18.8% | 25.4% | — | 28.5% | 5.7% | 开放 | 是 | 2026-08-12 |
| 134 | GPT-5.1 (high)历史 | OpenAI | 24.74* | 929.53 裁判协议 v4.3.1 | — | — | — | — | 80% | 37.7% | 51.9% | — | 28.5% | 4.9% | 闭源 | 是 | 2025-11-13 |
| 135 | Claude Sonnet 4.6 (Non-reasoning, high)历史 | Anthropic | 24.69* | — | — | — | — | — | 68.3% | 38.6% | 68.5% | — | 13.3% | 0.9% | 闭源 | 否 | 2026-02-17 |
| 136 | DeepSeek V4 Flash (max)历史 | DeepSeek | 24.63 | 1,115.64 裁判协议 v4.3.1 | 833.07 裁判协议 v4.3.1 | 28% | 2.5% | 45.3% | 74.3% | 36.8% | 96.1% | 10.8% | 34.8% | 7.1% | 开放 | 是 | 2026-04-24 |
| 137 | GPT-5.4 mini (xhigh)历史 | OpenAI | 24.58 | 1,094.54 裁判协议 v4.3.1 | 719.24 裁判协议 v4.3.1 | 26.2% | 2% | 52.1% | 77% | 37.5% | 90.2% | 13.4% | 28.1% | 10% | 闭源 | 是 | 2026-03-17 |
| 138 | Grok 4.3 (low)历史 | SpaceXAI | 24.3* | — | — | — | — | — | 74% | 26.7% | 17.4% | — | 18.4% | 0.6% | 闭源 | 是 | 2026-04-30 |
| 139 | GLM-5.1 (Non-reasoning)历史 | Z AI | 24.24* | — | — | — | — | — | 53.3% | 25.2% | 63.6% | — | 27.9% | 0% | 开放 | 否 | 2026-04-07 |
| 140 | MiMo-V2-Omni历史 | Xiaomi | 23.92* | — | — | — | — | — | 75% | 19.3% | 48.9% | — | 22.1% | 1.1% | 闭源 | 是 | 2026-03-19 |
| 141 | Gemini 3.5 Flash (minimal)历史 | 23.85* | — | — | — | — | — | 61.3% | 43% | 74.3% | — | 24.1% | 1.4% | 闭源 | 否 | 2026-05-19 | |
| 142 | GPT-5.1 Codex (high)历史 | OpenAI | 23.7* | — | — | — | — | — | 69.3% | 39.9% | 77.2% | — | 25.7% | 5.7% | 闭源 | 是 | 2025-11-13 |
| 143 | Claude Opus 4.5 (Non-reasoning)历史 | Anthropic | 23.68* | — | — | — | — | — | 70.7% | 40.9% | 76.2% | — | 13.2% | 0.3% | 闭源 | 否 | 2025-11-24 |
| 144 | Kimi K2.6 (Non-reasoning)历史 | Kimi | 23.57* | — | — | — | — | — | 69.7% | 24.3% | 44.2% | — | 19.6% | 1.4% | 开放 | 否 | 2026-04-20 |
| 145 | GLM 5V Turbo历史 | Z AI | 23.5* | — | — | — | — | — | 70.3% | 29.3% | 68.8% | — | 17.1% | 0.6% | 闭源 | 是 | 2026-04-01 |
| 146 | Kimi K2.5历史 | Kimi | 23.46* | 936.32 裁判协议 v4.3.1 | — | — | — | — | 78% | 35.2% | 65.7% | — | 30.7% | 3.1% | 开放 | 是 | 2026-01-27 |
| 147 | Nemotron 3 Ultra | NVIDIA | 23.41 | 1,090.88 裁判协议 v4.3.1 | 878.22 裁判协议 v4.3.1 | 3% | 0.5% | 40.3% | 79.3% | 22.6% | 29.7% | 5% | 28.4% | 3.1% | 开放 | 是 | 2026-06-04 |
| 148 | Claude Sonnet 4.6 (Non-reasoning, low)历史 | Anthropic | 23.3* | — | — | — | — | — | 69.3% | 36.5% | 60.8% | — | 11.2% | 0.9% | 闭源 | 否 | 2026-02-17 |
| 149 | MiniMax-M2.7历史 | MiniMax | 23.22 | 1,087.02 裁判协议 v4.3.1 | 715.25 裁判协议 v4.3.1 | 4.4% | 0% | 50.1% | 78.3% | 26.8% | 35.6% | 6% | 29.6% | 0.6% | 开放 | 是 | 2026-03-18 |
| 150 | GPT-5.5 (Non-reasoning)历史 | OpenAI | 23.17* | 1,054.41 裁判协议 v4.3.1 | — | — | — | — | 64% | 45.6% | 92.7% | — | 13.7% | 1.4% | 闭源 | 否 | 2026-04-23 |
| 151 | Ling-3.0-flash-Fin | InclusionAI | 23.02 | 1,170.55 裁判协议 v4.3.1 | 967.05 裁判协议 v4.3.1 | 7.4% | 0% | 42.4% | 73.7% | 17.9% | 39.5% | 5.4% | 22.6% | 2.6% | 开放 | 是 | 2026-09-11 |
| 152 | GPT-5 (high)历史 | OpenAI | 22.98* | 1,014.92 裁判协议 v4.3.1 | — | — | — | — | 78.2% | 40.3% | 82.2% | — | 28.5% | 5.7% | 闭源 | 是 | 2025-08-07 |
| 153 | Qwen3.5 27B历史 | Alibaba | 22.9* | — | — | — | — | — | 77.7% | 20.7% | 81.5% | — | 23.9% | 0.9% | 开放 | 是 | 2026-02-24 |
| 154 | GPT-5 (medium)历史 | OpenAI | 22.87* | — | — | — | — | — | 76% | 39.5% | 83.2% | — | 25.4% | 0% | 闭源 | 是 | 2025-08-07 |
| 155 | MiniMax-M2.5历史 | MiniMax | 22.8* | — | — | — | — | — | 73.3% | 26.2% | 88.1% | — | 20.5% | 1.1% | 开放 | 是 | 2026-02-12 |
| 156 | Hy3-preview历史 | Tencent | 22.74* | — | — | — | — | — | 64.7% | 27.9% | 87.4% | — | 27.8% | 4.6% | 开放 | 是 | 2026-04-23 |
| 157 | A.X-K2 | SK Telecom | 22.7* | 1,044.19 裁判协议 v4.3.1 | — | — | — | 41% | 70% | 18.6% | 33% | — | 29.6% | 8.9% | 开放 | 是 | 2026-08-12 |
| 158 | GPT-5.5 Instant (May 2026)历史 | OpenAI | 22.69* | — | — | — | — | — | 66.3% | 46.3% | 65.3% | — | 21.6% | 2.6% | 闭源 | 是 | 2026-05-05 |
| 159 | Gemini 3.5 Flash-Lite | 22.66 | 1,063.25 裁判协议 v4.3.1 | 645.32 裁判协议 v4.3.1 | 25% | 1% | 41.3% | 76% | 29.5% | 34.4% | 13.6% | 18.8% | 0% | 闭源 | 是 | 2026-07-21 | |
| 160 | Grok 4历史 | SpaceXAI | 22.49* | — | — | — | — | — | 68% | 40.5% | 64.5% | — | 26.7% | 2% | 闭源 | 是 | 2025-07-10 |
| 161 | MiMo-V2-Flash (Feb 2026) | Xiaomi | 22.44* | — | — | — | — | — | 71.3% | 19.8% | 48.4% | — | 22.1% | 2.9% | 开放 | 是 | 2025-12-16 |
| 162 | GLM-5.2 (Non-reasoning)历史 | Z AI | 22.43* | 1,306.43 裁判协议 v4.3.1 | — | — | — | — | 42.3% | 20.3% | 33.7% | — | 9.8% | 3.1% | 开放 | 否 | 2026-06-16 |
| 163 | Qwen3.8 27B | Alibaba | 22.42* | 1,113.3 裁判协议 v4.3.1 | — | 12.4% | — | 36.2% | 69.3% | 8.6% | 18.1% | — | 12.1% | 0.3% | 开放 | 否 | 2026-08-14 |
| 164 | Gemini 3 Pro Preview (low)历史 | 22.32* | — | — | — | — | — | 74% | 48.3% | 90% | — | 29.5% | 0% | 闭源 | 是 | 2025-11-18 | |
| 165 | MiMo-V2.5 | Xiaomi | 22.3 | 1,079.43 裁判协议 v4.3.1 | 750.72 裁判协议 v4.3.1 | 18.4% | 0% | 43.9% | 73% | 16.8% | 31.9% | 4% | 27.2% | 3.7% | 开放 | 是 | 2026-04-22 |
| 166 | GLM-4.7历史 | Z AI | 22.24* | 1,095.87 裁判协议 v4.3.1 | — | — | — | — | 71% | 29.3% | 93% | — | 27.4% | 1.7% | 开放 | 是 | 2025-12-22 |
| 167 | Kimi K2 Thinking历史 | Kimi | 22.02* | — | — | — | — | — | 72% | 30.9% | 75.6% | — | 23.8% | 2.6% | 开放 | 是 | 2025-11-06 |
| 168 | Qwen3.6 27B历史 | Alibaba | 21.91 | 1,068.87 裁判协议 v4.3.1 | 812.14 裁判协议 v4.3.1 | 11% | 0% | 42.8% | 77.3% | 19.6% | 49.3% | 11% | 23.1% | 1.1% | 开放 | 是 | 2026-04-22 |
| 169 | G9v3-39A5B | AI9Stars | 21.83* | 1,188.86 裁判协议 v4.3.1 | — | — | — | 36.8% | 65.3% | 14.9% | 13% | — | 17.5% | 0.3% | 开放 | 是 | 2026-08-20 |
| 170 | GLM-5 (Non-reasoning)历史 | Z AI | 21.78* | — | — | — | — | — | 43.7% | 23.1% | 45.3% | — | 7.6% | 0% | 开放 | 否 | 2026-02-11 |
| 171 | KAT-Coder-Pro V2 | KwaiKAT | 21.7* | 843.25 裁判协议 v4.3.1 | — | — | — | — | 73% | 21.5% | 56% | — | 16.1% | 0% | 闭源 | 否 | 2026-03-27 |
| 172 | GPT-5.6 Luna (low) | OpenAI | 21.55 | 1,075.16 裁判协议 v4.3.1 | 743.81 裁判协议 v4.3.1 | 11.7% | 0% | 46.1% | 70% | 39.6% | 89.9% | 14.2% | 19.8% | 2.6% | 闭源 | 是 | 2026-07-09 |
| 173 | DeepSeek V3.2历史 | DeepSeek | 21.49* | 810.24 裁判协议 v4.3.1 | — | — | — | — | 73.3% | 33% | 82.7% | — | 24.6% | 2.9% | 开放 | 是 | 2025-12-01 |
| 174 | Qwen3.5 397B A17B (Non-reasoning) | Alibaba | 21.44* | — | — | — | — | — | 64.3% | 24.5% | 82.7% | — | 19.8% | 0.9% | 开放 | 否 | 2026-02-16 |
| 175 | Qwen3 Max Thinking历史 | Alibaba | 21.26* | — | — | — | — | — | 74.3% | 29.8% | 94.7% | — | 28% | 1.7% | 闭源 | 是 | 2026-01-26 |
| 176 | GPT-5.4 nano (xhigh)历史 | OpenAI | 21.24 | 1,035.42 裁判协议 v4.3.1 | 669.58 裁判协议 v4.3.1 | 6% | 0.5% | 47.2% | 76.7% | 25.7% | 74.2% | 7.8% | 28.3% | 9.3% | 闭源 | 是 | 2026-03-17 |
| 177 | GPT-5.6 Terra (Non-reasoning) | OpenAI | 21.21 | 1,145.71 裁判协议 v4.3.1 | 947.67 裁判协议 v4.3.1 | 12.5% | 0.5% | 45.1% | 58.7% | 36.8% | 95% | 11.2% | 11.4% | 2% | 闭源 | 否 | 2026-07-09 |
| 178 | Claude 4.5 Sonnet历史 | Anthropic | 21.18 | 989.26 裁判协议 v4.3.1 | 711.96 裁判协议 v4.3.1 | 14.1% | 0% | 45.7% | 72.3% | 32.9% | 49.1% | 5.2% | 17.8% | 1.1% | 闭源 | 是 | 2025-09-29 |
| 179 | K2 Horizon 7B | Institute of Foundation Models | 21.05 | 1,091.08 裁判协议 v4.3.1 | 1,020.86 裁判协议 v4.3.1 | 20.9% | 1% | 27.5% | 69.7% | 12.8% | 33.6% | 3.2% | 18.2% | 0.3% | 开放 | 是 | 2026-09-03 |
| 180 | MiniMax-M2.1历史 | MiniMax | 20.95* | — | — | — | — | — | 67.7% | 21.2% | 68.5% | — | 23.2% | 0.3% | 开放 | 是 | 2025-12-23 |
| 181 | DeepSeek V4 Pro (Non-reasoning)历史 | DeepSeek | 20.83* | — | — | — | — | — | 53% | 30.9% | 87.8% | — | 8.2% | 0.9% | 开放 | 否 | 2026-04-24 |
| 182 | MiMo-V2-Flash历史 | Xiaomi | 20.82* | — | — | — | — | — | 70.7% | 24.8% | 93.4% | — | 22.8% | 4.3% | 开放 | 是 | 2025-12-16 |
| 183 | GPT-5 (low)历史 | OpenAI | 20.79* | — | — | — | — | — | — | 38.1% | 79% | — | 19.6% | 1.1% | 闭源 | 是 | 2025-08-07 |
| 184 | Ling 3.0 Flash | InclusionAI | 20.63 | 1,017.28 裁判协议 v4.3.1 | 802.47 裁判协议 v4.3.1 | 3.2% | 0% | 42% | 73% | 18.2% | 44.1% | 5.4% | 23.7% | 1.7% | 开放 | 是 | 2026-08-04 |
| 185 | GPT-5 mini (medium)历史 | OpenAI | 20.6* | — | — | — | — | — | 72.3% | 23.1% | 44.3% | — | 15.9% | 1.4% | 闭源 | 是 | 2025-08-07 |
| 186 | Qwen3.5 Omni Plus | Alibaba | 20.38* | — | — | — | — | — | 63.7% | 17.4% | 37% | — | 14.9% | 0.6% | 闭源 | 否 | 2026-03-30 |
| 187 | GPT-5.1 Codex mini (high)历史 | OpenAI | 20.38* | — | — | — | — | — | 66.7% | 23.2% | 51.6% | — | 18.5% | 0% | 闭源 | 是 | 2025-11-13 |
| 188 | Grok 4.1 Fast历史 | SpaceXAI | 20.37* | — | — | — | — | — | 74% | 25.1% | 73.4% | — | 19.3% | 2.9% | 闭源 | 是 | 2025-11-19 |
| 189 | o3 | OpenAI | 20.2* | — | — | — | — | — | 74.7% | 38.6% | 88.1% | — | 20.1% | 1.1% | 闭源 | 是 | 2025-04-16 |
| 190 | GPT-5.4 nano历史 | OpenAI | 20.01* | — | — | — | — | — | 67.3% | 21.9% | 51.1% | — | 15.9% | 5.1% | 闭源 | 是 | 2026-03-17 |
| 191 | Qwen3.6 27B (Non-reasoning)历史 | Alibaba | 19.83* | 1,042.8 裁判协议 v4.3.1 | — | — | — | — | 66.7% | 16.7% | 84% | — | 15.1% | 0.9% | 开放 | 否 | 2026-04-22 |
| 192 | GPT-5.4 mini (medium)历史 | OpenAI | 19.75* | — | — | — | — | — | 67% | 36.5% | 89.8% | — | 18.6% | 2.9% | 闭源 | 是 | 2026-03-17 |
| 193 | K-EXAONE 2.0 | LG AI Research | 19.69* | 918 裁判协议 v4.3.1 | — | — | — | 42% | 60% | 13.1% | 22.6% | — | 18.6% | 0.9% | 开放 | 是 | 2026-08-12 |
| 194 | LongCat 2.0 | LongCat | 19.69 | 964.51 裁判协议 v4.3.1 | 738.88 裁判协议 v4.3.1 | 4.5% | 0% | 36.3% | 65% | 29.6% | 75.4% | 6.4% | 33.7% | 2.6% | 开放 | 是 | 2026-06-29 |
| 195 | Step 3.7 Flash | StepFun | 19.48* | 954.2 裁判协议 v4.3.1 | — | — | — | 43.9% | 73.7% | 25.8% | 85% | — | 21.4% | 2.3% | 开放 | 是 | 2026-05-29 |
| 196 | Kimi K2.5 (Non-reasoning)历史 | Kimi | 19.43* | — | — | — | — | — | 67.3% | 24.1% | 50% | — | 13.2% | 0.6% | 开放 | 否 | 2026-01-27 |
| 197 | Qwen3.5 27B (Non-reasoning)历史 | Alibaba | 19.37* | — | — | — | — | — | 64% | 15.7% | 75.1% | — | 13.9% | 0.3% | 开放 | 否 | 2026-02-24 |
| 198 | Claude 4.5 Sonnet (Non-reasoning)历史 | Anthropic | 19.34* | — | — | — | — | — | 54% | 28.4% | 52.7% | — | 7.2% | 0% | 闭源 | 否 | 2025-09-29 |
| 199 | Qwen3.5 35B A3B历史 | Alibaba | 19.33* | — | — | — | — | — | 72% | 20.1% | 85.4% | — | 21% | 0.9% | 开放 | 是 | 2026-02-24 |
| 200 | Qwen3.5 397B A17B | Alibaba | 19.11 | 905.4 裁判协议 v4.3.1 | 562.65 裁判协议 v4.3.1 | 6.9% | 0% | 44.8% | 77.3% | 30.8% | 88.9% | 12.2% | 29% | 1.7% | 开放 | 是 | 2026-02-16 |
| 201 | Claude 4 Sonnet历史 | Anthropic | 18.92* | 818.93 裁判协议 v4.3.1 | — | — | — | — | 70.3% | 22.7% | 29.1% | — | 10.7% | 0.3% | 闭源 | 是 | 2025-05-22 |
| 202 | DeepSeek V4 Flash (Non-reasoning)历史 | DeepSeek | 18.88* | — | — | — | — | — | 41.7% | 26% | 94.5% | — | 7.8% | 0.3% | 开放 | 否 | 2026-04-24 |
| 203 | Qwen3.6 35B A3B | Alibaba | 18.81 | 990.51 裁判协议 v4.3.1 | 711.46 裁判协议 v4.3.1 | 5.2% | 0% | 36.6% | 71.7% | 18.8% | 50.5% | 6.6% | 22.2% | 0.3% | 开放 | 是 | 2026-04-16 |
| 204 | JT-35B-Flash | China Mobile | 18.66* | — | — | — | — | — | 65.7% | 24.2% | 63.8% | — | 6.4% | 0% | 闭源 | 否 | 2026-05-14 |
| 205 | MiniMax-M2历史 | MiniMax | 18.63* | — | — | — | — | — | 64.3% | 23.2% | 90.9% | — | 13.7% | 0.9% | 开放 | 是 | 2025-10-26 |
| 206 | KAT-Coder-Pro V1历史 | KwaiKAT | 18.59* | 845.3 裁判协议 v4.3.1 | 602.09 裁判协议 v4.3.1 | — | — | — | 38.7% | 17.7% | 67.4% | — | 33.6% | 0% | 闭源 | 否 | 2025-11-11 |
| 207 | GLM-4.6历史 | Z AI | 18.53* | 873.8 裁判协议 v4.3.1 | — | — | — | — | 54% | 26.9% | 94.1% | — | 14.5% | 1.1% | 开放 | 是 | 2025-09-30 |
| 208 | MiMo-V2.5-Pro (Non-reasoning) | Xiaomi | 18.29* | — | — | — | — | — | 41.7% | 27.2% | 89.2% | — | 14.8% | 1.1% | 开放 | 否 | 2026-04-22 |
| 209 | GPT-5.4 (Non-reasoning)历史 | OpenAI | 18.16* | — | — | — | — | — | 58.3% | 37.4% | 84.7% | — | 11.3% | 0.6% | 闭源 | 否 | 2026-03-05 |
| 210 | Muse Glimmer (high) | Meta | 18.07 | 892.72 裁判协议 v4.3.1 | 481.02 裁判协议 v4.3.1 | 6.8% | 0.5% | 44.9% | 83.3% | 27% | 81.9% | 10% | 22% | 2.6% | 开放 | 是 | 2026-08-10 |
| 211 | Grok 4 Fast历史 | SpaceXAI | 17.94* | — | — | — | — | — | 73.7% | 22.8% | 68.3% | — | 19.1% | 2.9% | 闭源 | 是 | 2025-09-19 |
| 212 | Gemini 3 Flash (Non-reasoning)历史 | 17.93* | — | — | — | — | — | 55.3% | 45.8% | 92.4% | — | 15% | 1.4% | 闭源 | 否 | 2025-12-17 | |
| 213 | Qwen3.5 122B A10B (Non-reasoning) | Alibaba | 17.75* | 833.05 裁判协议 v4.3.1 | — | — | — | — | 61.3% | 19.1% | 91.6% | — | 15.9% | 0.9% | 开放 | 否 | 2026-02-24 |
| 214 | Claude 3.7 Sonnet历史 | Anthropic | 17.71* | — | — | — | — | — | — | 28% | 40% | — | 9.7% | 0.9% | 闭源 | 是 | 2025-02-24 |
| 215 | Claude 4.5 Haiku | Anthropic | 17.59 | 854.45 裁判协议 v4.3.1 | 614.13 裁判协议 v4.3.1 | 3.2% | 0% | 42.2% | 74.3% | 18% | 27.3% | 3.8% | 10.4% | 0% | 闭源 | 是 | 2025-10-15 |
| 216 | GPT-5 mini (high)历史 | OpenAI | 17.41 | 880.27 裁判协议 v4.3.1 | 437.58 裁判协议 v4.3.1 | 6.5% | 0% | 39% | 72.3% | 25% | 56.4% | 8.4% | 21.5% | 0% | 闭源 | 是 | 2025-08-07 |
| 217 | GLM-4.7 (Non-reasoning)历史 | Z AI | 17.36* | — | — | — | — | — | 40.7% | 23.6% | 92.9% | — | 6.4% | 0% | 开放 | 否 | 2025-12-22 |
| 218 | Ring-2.6-1T | InclusionAI | 17.28 | 863.62 裁判协议 v4.3.1 | 654.34 裁判协议 v4.3.1 | 0.7% | 0.5% | 45% | 70% | 25.7% | 85.3% | 3.8% | 21.6% | 3.7% | 开放 | 是 | 2026-05-08 |
| 219 | Hy3-preview (Non-reasoning)历史 | Tencent | 17.04* | — | — | — | — | — | 42% | 23.2% | 75.7% | — | 7% | 0.3% | 开放 | 否 | 2026-04-23 |
| 220 | Ling-2.6-1T历史 | InclusionAI | 17* | — | — | — | — | — | 41.7% | 21.9% | 92.8% | — | 8.7% | 0.3% | 开放 | 否 | 2026-04-23 |
| 221 | GPT-5.2 (Non-reasoning)历史 | OpenAI | 16.98* | — | — | — | — | — | 45.7% | 30.9% | 62.3% | — | 8% | 0.6% | 闭源 | 否 | 2025-12-11 |
| 222 | Step 3.5 Flash 2603历史 | StepFun | 16.96* | — | — | — | — | — | 63% | 24.6% | 91.3% | — | 24.5% | 2.3% | 闭源 | 是 | 2026-04-02 |
| 223 | Doubao Seed Code | ByteDance Seed | 16.95* | — | — | — | — | — | 71.7% | 24.9% | 80% | — | 14.1% | 0.3% | 闭源 | 是 | 2025-11-11 |
| 224 | Gemma 4 26B A4B | 16.67* | 693 裁判协议 v4.3.1 | — | — | — | 40% | 65.7% | 19.1% | 86.4% | — | 19.3% | 0% | 开放 | 是 | 2026-04-02 | |
| 225 | Gemini 2.5 Pro历史 | 16.66 | 615.9 裁判协议 v4.3.1 | 315.4 裁判协议 v4.3.1 | 2.2% | 0% | 46.3% | 69% | 39.1% | 90.9% | 10.2% | 22.5% | 2.6% | 闭源 | 是 | 2025-06-05 | |
| 226 | o4-mini (high)历史 | OpenAI | 16.65* | — | — | — | — | — | 61% | 24.8% | 80.5% | — | 16.5% | 0.6% | 闭源 | 是 | 2025-04-16 |
| 227 | Step 3.5 Flash历史 | StepFun | 16.62* | — | — | — | — | — | 50% | 23.6% | 85.7% | — | 21.1% | 2.5% | 开放 | 是 | 2026-02-02 |
| 228 | Claude 4 Sonnet (Non-reasoning)历史 | Anthropic | 16.61* | — | — | — | — | — | 44% | 22.7% | 41% | — | 4.3% | 1.1% | 闭源 | 否 | 2025-05-22 |
| 229 | DeepSeek V3.2 Exp历史 | DeepSeek | 16.58* | — | — | — | — | — | 72.3% | 27.6% | 80.8% | — | 14.9% | 1.4% | 开放 | 是 | 2025-09-29 |
| 230 | Qwen3 Max Thinking (Preview)历史 | Alibaba | 16.29* | — | — | — | — | — | 62% | 27.4% | 91.5% | — | 12.7% | 0% | 闭源 | 是 | 2025-11-03 |
| 231 | Qwen3.5 122B A10B | Alibaba | 16.19 | 925.2 裁判协议 v4.3.1 | 498.94 裁判协议 v4.3.1 | 5.5% | 0% | 39.7% | 76.3% | 24.4% | 87.1% | 3.4% | 25.2% | 0.6% | 开放 | 是 | 2026-02-24 |
| 232 | K2 Horizon 3.7B | Institute of Foundation Models | 16.16 | 962.39 裁判协议 v4.3.1 | 792.8 裁判协议 v4.3.1 | 14.7% | 0% | 22% | 62.3% | 10.8% | 44.1% | 3.2% | 13.9% | 0% | 开放 | 是 | 2026-09-03 |
| 233 | GPT-5.6 Luna (Non-reasoning) | OpenAI | 16.05 | 987.47 裁判协议 v4.3.1 | 710.24 裁判协议 v4.3.1 | 5% | 1% | 40.4% | 42.7% | 28.6% | 75% | 6% | 7.2% | 0.3% | 闭源 | 否 | 2026-07-09 |
| 234 | MiMo-V2-Flash (Non-reasoning)历史 | Xiaomi | 16.05* | 788.18 裁判协议 v4.3.1 | — | — | — | — | 36.3% | 15.6% | 76% | — | 8.6% | 0% | 开放 | 否 | 2025-12-16 |
| 235 | DeepSeek V3.2 (Non-reasoning)历史 | DeepSeek | 16.04* | — | — | — | — | — | 45.7% | 24% | 93.3% | — | 11.2% | 0.9% | 开放 | 否 | 2025-12-01 |
| 236 | Gemini 3.1 Flash-Lite历史 | 16.03 | 595.99 裁判协议 v4.3.1 | 226.15 裁判协议 v4.3.1 | 6.8% | 0.5% | 43.4% | 74.3% | 36.3% | 82.7% | 7.8% | 17.2% | 1.1% | 闭源 | 是 | 2026-03-03 | |
| 237 | Qwen3 Max历史 | Alibaba | 15.61* | — | — | — | — | — | 50% | 24.4% | 89.9% | — | 11.9% | 0% | 闭源 | 否 | 2025-09-23 |
| 238 | Gemini 2.5 Flash (Sep)历史 | 15.47* | — | — | — | — | — | 71% | 28.3% | 89.9% | — | 13.8% | 0.3% | 闭源 | 是 | 2025-09-25 | |
| 239 | Gemma 4 31B | 15.42 | 755.45 裁判协议 v4.3.1 | 376.57 裁判协议 v4.3.1 | 4.9% | 0% | 45.5% | 69.7% | 20% | 85% | 6% | 23.6% | 1.4% | 开放 | 是 | 2026-04-02 | |
| 240 | Claude 4.5 Haiku (Non-reasoning) | Anthropic | 15.41* | — | — | — | — | — | 49.7% | 14.4% | 25.7% | — | 4.2% | 0% | 闭源 | 否 | 2025-10-15 |
| 241 | DeepSeek V3.1 Terminus历史 | DeepSeek | 15.4 | 826.12 裁判协议 v4.3.1 | 464.01 裁判协议 v4.3.1 | 2.7% | 0% | 38% | 69.3% | 27.7% | 74.8% | 5.4% | 16.4% | 1.7% | 开放 | 是 | 2025-09-22 |
| 242 | Kimi K2 0905历史 | Kimi | 15.29* | — | — | — | — | — | 53% | 25.4% | 69.7% | — | 6.4% | 0% | 开放 | 否 | 2025-09-05 |
| 243 | Claude 3.7 Sonnet (Non-reasoning)历史 | Anthropic | 15.27* | — | — | — | — | — | 51.7% | 28.2% | 52.8% | — | 4.2% | 0% | 闭源 | 否 | 2025-02-24 |
| 244 | Qwen3.6 35B A3B (Non-reasoning) | Alibaba | 15.23* | 953.19 裁判协议 v4.3.1 | — | — | — | — | 64.3% | 16.7% | 92.1% | — | 13.9% | 0% | 开放 | 否 | 2026-04-16 |
| 245 | o1历史 | OpenAI | 15.23* | — | — | — | — | — | 65% | 34.5% | 69.6% | — | 7% | 0.3% | 闭源 | 是 | 2024-12-05 |
| 246 | Qwen3.5 35B A3B (Non-reasoning)历史 | Alibaba | 15.12* | 740.47 裁判协议 v4.3.1 | — | — | — | — | 63% | 15.7% | 93.4% | — | 13.4% | 0.6% | 开放 | 否 | 2026-02-24 |
| 247 | GLM-4.6 (Non-reasoning)历史 | Z AI | 14.93* | — | — | — | — | — | 26.3% | 21.4% | 67.6% | — | 5.5% | 0% | 开放 | 否 | 2025-09-30 |
| 248 | Mistral Medium 3.5 | Mistral | 14.89 | 875.14 裁判协议 v4.3.1 | 523.63 裁判协议 v4.3.1 | 6.3% | 0% | 40.2% | 69.3% | 24.7% | 81.6% | 2.8% | 13.8% | 0% | 开放 | 是 | 2026-04-29 |
| 249 | GLM-4.7-Flash历史 | Z AI | 14.87* | — | — | — | — | — | 41.7% | 16.2% | 93.9% | — | 7.6% | 0.3% | 开放 | 是 | 2026-01-19 |
| 250 | Granite 4.2 30B | IBM | 14.83* | 721.01 裁判协议 v4.3.1 | — | — | — | 37.8% | 49% | 10.1% | 25.6% | 1.8% | 11.2% | 0.3% | 开放 | 是 | 2026-08-25 |
| 251 | Grok 3 mini Reasoning (high)历史 | SpaceXAI | 14.62* | — | — | — | — | — | 55.3% | 15.1% | 25.8% | — | 11% | 0.6% | 闭源 | 是 | 2025-02-19 |
| 252 | Grok 4.20 0309 (Non-reasoning)历史 | SpaceXAI | 14.61* | — | — | — | — | — | 25.3% | 26.1% | 92.8% | — | 24.5% | 0% | 闭源 | 否 | 2026-03-10 |
| 253 | Grok 4.3 (Non-reasoning)历史 | SpaceXAI | 14.54 | 1,030.8 裁判协议 v4.3.1 | 724.4 裁判协议 v4.3.1 | 0.9% | 0% | 39.4% | 32.3% | 23.7% | 74.5% | 2.8% | 6.8% | 0% | 闭源 | 否 | 2026-04-30 |
| 254 | DeepSeek V3.2 Speciale历史 | DeepSeek | 14.46* | — | — | — | — | — | 70% | 37.8% | 89.2% | — | 28.7% | 7.4% | 开放 | 是 | 2025-12-01 |
| 255 | K-EXAONE历史 | LG AI Research | 14.37* | 539.71 裁判协议 v4.3.1 | — | — | — | — | 61.3% | 16.4% | 88.8% | — | 13.9% | 1.1% | 开放 | 是 | 2025-12-31 |
| 256 | ERNIE 5.0 Thinking Preview | Baidu | 14.26* | — | — | — | — | — | — | 22.1% | 87% | — | 13.3% | 1.4% | 闭源 | 是 | 2025-11-13 |
| 257 | Grok 4.20 0309 v2 (Non-reasoning)历史 | SpaceXAI | 14.2* | — | — | — | — | — | 23.3% | 26.7% | 97.3% | — | 27.9% | 0.3% | 闭源 | 否 | 2026-04-07 |
| 258 | Gemma 4 12B | 14.18* | 590.73 裁判协议 v4.3.1 | — | — | — | — | 63.7% | 15.6% | 81% | — | 15.7% | 0% | 开放 | 是 | 2026-06-03 | |
| 259 | Nova 2.0 Pro Preview (medium) | Amazon | 14.16* | 629.57 裁判协议 v4.3.1 | — | — | — | — | 64% | 22% | 91% | — | 9.4% | 0% | 闭源 | 是 | 2025-11-27 |
| 260 | Grok Code Fast 1历史 | SpaceXAI | 14.06* | — | — | — | — | — | 53% | 23.5% | 79.3% | — | 8% | 0% | 闭源 | 是 | 2025-08-28 |
| 261 | DeepSeek V3.1 Terminus (Non-reasoning)历史 | DeepSeek | 13.93* | — | — | — | — | — | 45.3% | 23.5% | 87.6% | — | 8.7% | 0% | 开放 | 否 | 2025-09-22 |
| 262 | Command A+ | Cohere | 13.92 | 658.08 裁判协议 v4.3.1 | 366.16 裁判协议 v4.3.1 | 1.8% | 0.5% | 38.5% | 52.7% | 8.9% | 14.2% | 1% | 12% | 0.3% | 开放 | 是 | 2026-05-20 |
| 263 | Gemma 4 31B (Non-reasoning) | 13.92* | 691.46 裁判协议 v4.3.1 | — | — | — | — | 46.7% | 16.6% | 81.9% | — | 11.8% | 0% | 开放 | 否 | 2026-04-02 | |
| 264 | DeepSeek V3.2 Exp (Non-reasoning)历史 | DeepSeek | 13.88* | — | — | — | — | — | 44.7% | 22.8% | 92.1% | — | 9% | 1.4% | 开放 | 否 | 2025-09-29 |
| 265 | Apriel-v1.5-15B-Thinker历史 | ServiceNow | 13.82* | — | — | — | — | — | 21.3% | 16.4% | 85.3% | — | 12.1% | 1.1% | 开放 | 是 | 2025-09-30 |
| 266 | DeepSeek V3.1 (Non-reasoning)历史 | DeepSeek | 13.71* | — | — | — | — | — | 47% | 23.1% | 85.7% | — | 6.7% | 0% | 开放 | 否 | 2025-08-21 |
| 267 | Qwen3.5 9B | Alibaba | 13.65* | 588.42 裁判协议 v4.3.1 | — | — | — | — | 70% | 16.4% | 83.6% | — | 14.9% | 0.3% | 开放 | 是 | 2026-03-02 |
| 268 | Nova 2.0 Omni (medium) | Amazon | 13.65* | — | — | — | — | — | 59.7% | 17.7% | 93.3% | — | 7% | 0% | 闭源 | 是 | 2025-11-26 |
| 269 | Nemotron 3.5 Lightning | NVIDIA | 13.64 | 766.89 裁判协议 v4.3.1 | 508.5 裁判协议 v4.3.1 | 0.8% | 0.5% | 32.1% | 60.3% | 14.4% | 37.6% | 3% | 10.6% | 0% | 开放 | 是 | 2026-08-11 |
| 270 | Nemotron 3 Super | NVIDIA | 13.55 | 644.41 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 3.8% | 0% | 36.2% | 65.7% | 24.3% | 87% | 2.6% | 20.8% | 3.1% | 开放 | 是 | 2026-03-11 |
| 271 | DeepSeek V3.1历史 | DeepSeek | 13.48* | — | — | — | — | — | 56.7% | 29% | 82.5% | — | 14.3% | 2% | 开放 | 是 | 2025-08-21 |
| 272 | Qwen3 VL 235B A22B (Reasoning)历史 | Alibaba | 13.44* | — | — | — | — | — | 63.7% | 20.8% | 85.2% | — | 11.9% | 0% | 开放 | 是 | 2025-09-23 |
| 273 | Apriel-v1.6-15B-Thinker | ServiceNow | 13.4* | — | — | — | — | — | — | 17% | 91.9% | — | 10.8% | 0.3% | 开放 | 是 | 2025-11-25 |
| 274 | Nova 2.0 Lite (high) | Amazon | 13.37* | 535.99 裁判协议 v4.3.1 | — | — | — | — | 60.3% | 19% | 91.4% | — | 11.6% | 0.3% | 闭源 | 是 | 2025-10-29 |
| 275 | GPT-5.1 (Non-reasoning)历史 | OpenAI | 13.31* | — | — | — | — | — | 45% | 29.5% | 90.6% | — | 5.3% | 0% | 闭源 | 否 | 2025-11-13 |
| 276 | Qwen3.5 9B (Non-reasoning) | Alibaba | 13.27* | — | — | — | — | — | 46% | 14% | 98.4% | — | 9.4% | 0.6% | 开放 | 否 | 2026-03-02 |
| 277 | EXAONE 4.5 33B | LG AI Research | 13.21* | 627.65 裁判协议 v4.3.1 | — | — | — | — | 54.7% | 16.2% | 79.9% | — | 12.9% | 0.3% | 开放 | 是 | 2026-04-09 |
| 278 | MiniCPM5-2B | OpenBMB | 13.14 | 827.51 裁判协议 v4.3.1 | 433.52 裁判协议 v4.3.1 | 1.8% | 0% | 26.3% | 59.3% | 8.4% | 21.9% | 1.4% | 8.9% | 0.3% | 开放 | 是 | 2026-09-07 |
| 279 | Gemma 4 26B A4B (Non-reasoning) | 13.13* | — | — | — | — | — | 42.3% | 15.5% | 92.1% | — | 11.5% | 0% | 开放 | 否 | 2026-04-02 | |
| 280 | Qwen3.5 4B | Alibaba | 13.12* | — | — | — | — | — | 63% | 15.1% | 86.6% | — | 9.9% | 0% | 开放 | 是 | 2026-03-02 |
| 281 | DeepSeek R1 0528历史 | DeepSeek | 13.12* | — | — | — | — | — | 55.7% | 30.5% | 83.4% | — | 15.8% | 1.4% | 开放 | 是 | 2025-05-28 |
| 282 | Gemini 2.5 Flash历史 | 13.11* | — | — | — | — | — | 65.3% | 25.9% | 75.3% | — | 12.1% | 1.1% | 闭源 | 是 | 2025-05-20 | |
| 283 | GPT-5 nano (high)历史 | OpenAI | 12.99* | — | — | — | — | — | 45% | 19.1% | 59% | — | 9.5% | 0% | 闭源 | 是 | 2025-08-07 |
| 284 | Nova 2.0 Pro Preview (low) | Amazon | 12.78* | 600.77 裁判协议 v4.3.1 | — | — | — | — | 64.7% | 17.1% | 69.5% | — | 5.2% | 0% | 闭源 | 是 | 2025-11-27 |
| 285 | GLM-4.5历史 | Z AI | 12.77* | — | — | — | — | — | 52.7% | 25.1% | 70.1% | — | 13% | 0% | 开放 | 是 | 2025-07-28 |
| 286 | Kimi K2历史 | Kimi | 12.72* | — | — | — | — | — | 53% | 27.4% | 76.6% | — | 7.4% | 0% | 开放 | 否 | 2025-07-11 |
| 287 | Qwen3 235B A22B 2507历史 | Alibaba | 12.71 | 495.33 裁判协议 v4.3.1 | 189.93 裁判协议 v4.3.1 | 2.2% | 0% | 41.4% | 72% | 22.8% | 89.8% | 4.8% | 15.9% | 0% | 开放 | 是 | 2025-07-25 |
| 288 | GPT-4.1历史 | OpenAI | 12.69* | — | — | — | — | — | 68.3% | 27.8% | 93.3% | — | 4.2% | 0% | 闭源 | 否 | 2025-04-14 |
| 289 | Qwen3 Max (Preview)历史 | Alibaba | 12.59* | — | — | — | — | — | 43% | 24.2% | 88.4% | — | 10.1% | 0.9% | 闭源 | 否 | 2025-09-05 |
| 290 | Nova 2.0 Lite (medium) | Amazon | 12.48* | — | — | — | — | — | 60% | 18.2% | 91.8% | — | 9% | 0% | 闭源 | 是 | 2025-10-29 |
| 291 | GPT-5 nano (medium)历史 | OpenAI | 12.48* | — | — | — | — | — | 43.7% | 17.6% | 52.6% | — | 8.7% | 0% | 闭源 | 是 | 2025-08-07 |
| 292 | Qwen3.5 Omni Flash | Alibaba | 12.47* | — | — | — | — | — | 52% | 14.6% | 93.4% | — | 7.6% | 0% | 闭源 | 否 | 2026-03-30 |
| 293 | Gemini 2.5 Flash (Sep) (Non-reasoning)历史 | 12.38* | — | — | — | — | — | 60% | 26.8% | 91.2% | — | 8.7% | 0% | 闭源 | 否 | 2025-09-25 | |
| 294 | gpt-oss-120b (high) | OpenAI | 12.35 | 744.74 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.2% | 0% | 34% | 52% | 21.8% | 90.8% | 4% | 19.6% | 1.1% | 开放 | 是 | 2025-08-05 |
| 295 | JT-MINI | China Mobile | 12.21* | — | — | — | — | — | 13% | 14.2% | 91.3% | — | 6.4% | 0% | 闭源 | 否 | 2026-04-15 |
| 296 | Grok 3历史 | SpaceXAI | 12.11* | — | — | — | — | — | 58% | 28.9% | 87.3% | — | 4.1% | 0% | 闭源 | 否 | 2025-02-19 |
| 297 | Seed-OSS-36B-Instruct历史 | ByteDance Seed | 12.1* | — | — | — | — | — | 61.3% | 18.2% | 86.4% | — | 9.9% | 0% | 开放 | 是 | 2025-08-20 |
| 298 | Qwen3 235B 2507历史 | Alibaba | 12* | — | — | — | — | — | 33.9% | 18.7% | 77.2% | — | 11.1% | 0% | 开放 | 否 | 2025-07-21 |
| 299 | Qwen3 Coder 480B历史 | Alibaba | 11.9* | — | — | — | — | — | 45.7% | 15.7% | 44.9% | — | 4.5% | 0% | 开放 | 否 | 2025-07-22 |
| 300 | Qwen3 VL 32B (Reasoning)历史 | Alibaba | 11.87* | — | — | — | — | — | 55.3% | 17% | 83.7% | — | 10.1% | 0% | 开放 | 是 | 2025-10-21 |
| 301 | Ling 3.0 Tiny | InclusionAI | 11.87 | 715.64 裁判协议 v4.3.1 | 481.43 裁判协议 v4.3.1 | 0.3% | 0% | 24.2% | 60.3% | 8.5% | 30.5% | 0.8% | 9.3% | 0% | 开放 | 是 | 2026-08-06 |
| 302 | Magistral Medium 1.2 | Mistral | 11.83* | 361.94 裁判协议 v4.3.1 | — | — | — | — | 53% | 20.8% | 60% | — | 10.3% | 0.3% | 闭源 | 是 | 2025-09-18 |
| 303 | Granite 4.2 8B | IBM | 11.81 | 645.07 裁判协议 v4.3.1 | 320.12 裁判协议 v4.3.1 | 2.1% | 0% | 31.5% | 45% | 11.2% | 32% | 0.6% | 9.7% | 0.3% | 开放 | 是 | 2026-08-25 |
| 304 | Nova 2.0 Lite (low) | Amazon | 11.8* | — | — | — | — | — | 54.3% | 17.6% | 87.1% | — | 4% | 0% | 闭源 | 是 | 2025-10-29 |
| 305 | HyperNova 60B 2605 (high) | Multiverse Computing | 11.74* | 603.87 裁判协议 v4.3.1 | 249.39 裁判协议 v4.3.1 | — | — | — | 36.3% | 15.2% | 82.3% | — | 16.6% | 0.9% | 开放 | 是 | 2026-05-26 |
| 306 | MiniMax M1 80k历史 | MiniMax | 11.73* | — | — | — | — | — | 57.7% | 22.5% | 91.5% | — | 8.9% | 0% | 开放 | 是 | 2025-06-17 |
| 307 | GPT-5.4 nano (Non-reasoning)历史 | OpenAI | 11.69* | 680.74 裁判协议 v4.3.1 | — | — | — | — | 29.7% | 14.9% | 61.5% | — | 4.1% | 0% | 闭源 | 否 | 2026-03-17 |
| 308 | Nemotron Cascade 2 30B A3B | NVIDIA | 11.67* | 447.27 裁判协议 v4.3.1 | — | — | — | — | 39.3% | 18.3% | 85.4% | — | 12% | 0.6% | 开放 | 是 | 2026-03-19 |
| 309 | Mercury 2 | Inception | 11.51 | 646.34 裁判协议 v4.3.1 | 279.6 裁判协议 v4.3.1 | 1.7% | 0% | 37.7% | 43.7% | 21.2% | 91.2% | 3.8% | 17.1% | 0.8% | 闭源 | 是 | 2026-02-20 |
| 310 | K2 Think V2 | Institute of Foundation Models | 11.5* | 328.05 裁判协议 v4.3.1 | 34 裁判协议 v4.3.1 | — | — | — | 57% | 18% | 71.2% | — | 10.1% | 0% | 开放 | 是 | 2025-12-15 |
| 311 | LongCat Flash Lite | LongCat | 11.47* | — | — | — | — | — | 28.3% | 13.3% | 96.2% | — | 5.8% | 0% | 开放 | 否 | 2026-01-28 |
| 312 | Mistral Small 4 | Mistral | 11.45 | 536.71 裁判协议 v4.3.1 | 255.96 裁判协议 v4.3.1 | 1% | 0% | 38.8% | 49.7% | 21.7% | 66.5% | 0% | 9.9% | 0.3% | 开放 | 是 | 2026-03-16 |
| 313 | GPT-5 (minimal)历史 | OpenAI | 11.45* | — | — | — | — | — | — | 29.6% | 90.1% | — | 6% | 0% | 闭源 | 否 | 2025-08-07 |
| 314 | DeepSeek R1 (Jan)历史 | DeepSeek | 11.41 | 478.84 裁判协议 v4.3.1 | 149.56 裁判协议 v4.3.1 | 0.2% | 0% | 38.3% | 57.7% | 30.5% | 90.3% | 2.4% | 8.5% | 0.6% | 开放 | 是 | 2025-01-20 |
| 315 | HyperCLOVA X SEED Think (32B) | Naver | 11.36* | — | — | — | — | — | 13.7% | 15.4% | 81.2% | — | 5.5% | 0% | 开放 | 是 | 2025-12-26 |
| 316 | Grok 4.1 Fast (Non-reasoning)历史 | SpaceXAI | 11.28* | — | — | — | — | — | 31.3% | 17.2% | 82.3% | — | 5.1% | 0% | 闭源 | 否 | 2025-11-19 |
| 317 | GLM-4.6V历史 | Z AI | 11.22* | — | — | — | — | — | 48.7% | 16.2% | 51.5% | — | 9.6% | 0% | 开放 | 是 | 2025-12-08 |
| 318 | K-EXAONE (Non-reasoning)历史 | LG AI Research | 11.21* | — | — | — | — | — | 53.3% | 13.7% | 91.5% | — | 5.7% | 0% | 开放 | 否 | 2025-12-31 |
| 319 | Qwen3 Next 80B A3B (Reasoning) | Alibaba | 11.2* | 324.88 裁判协议 v4.3.1 | — | — | — | — | 63.7% | 19% | 87% | — | 12.6% | 0% | 开放 | 是 | 2025-09-11 |
| 320 | GPT-5.4 mini (Non-reasoning)历史 | OpenAI | 11.14* | 734.27 裁判协议 v4.3.1 | — | — | — | — | 37% | 25.7% | 95.6% | — | 5.9% | 0% | 闭源 | 否 | 2026-03-17 |
| 321 | Nova 2.0 Omni (low) | Amazon | 11.11* | — | — | — | — | — | 57.7% | 18.6% | 84.7% | — | — | 0% | 闭源 | 是 | 2025-11-26 |
| 322 | GLM-4.5-Air历史 | Z AI | 11.09* | — | — | — | — | — | 46.7% | 16.3% | 92.9% | — | 7% | 0% | 开放 | 是 | 2025-07-28 |
| 323 | Grok 4 Fast (Non-reasoning)历史 | SpaceXAI | 11.06* | — | — | — | — | — | 24% | 17.7% | 87.6% | — | 4.5% | 0% | 闭源 | 否 | 2025-09-19 |
| 324 | Mi:dm K 2.5 Pro | Korea Telecom | 11.04* | — | — | — | — | — | 9% | 17.9% | 93.9% | — | 8.1% | 0% | 闭源 | 是 | 2025-12-11 |
| 325 | o3-mini (high)历史 | OpenAI | 10.96 | 420.79 裁判协议 v4.3.1 | 161.06 裁判协议 v4.3.1 | 0.5% | 0% | 42.8% | 43% | 21.3% | 81.1% | 2% | 12% | 0.3% | 闭源 | 是 | 2025-01-31 |
| 326 | Ring-1T历史 | InclusionAI | 10.9* | — | — | — | — | — | 54.7% | 20.5% | 89.8% | — | 11.1% | 0.6% | 开放 | 是 | 2025-10-13 |
| 327 | Trinity Large Thinking | Arcee AI | 10.88 | 511.58 裁判协议 v4.3.1 | 271.11 裁判协议 v4.3.1 | 1.3% | 0.5% | 40.6% | 38% | 22.5% | 85.9% | 1.2% | 15.8% | 0.9% | 开放 | 是 | 2026-04-01 |
| 328 | G9v3-3B | AI9Stars | 10.84* | 807.38 裁判协议 v4.3.1 | — | — | — | — | 41.3% | 6.5% | 11.7% | — | 4.5% | 0% | 开放 | 是 | 2026-07-23 |
| 329 | Qwen3.5 4B (Non-reasoning) | Alibaba | 10.81* | — | — | — | — | — | 34.7% | 11.2% | 96.8% | — | 8% | 0% | 开放 | 否 | 2026-03-02 |
| 330 | INTELLECT-3 | Prime Intellect | 10.61* | — | — | — | — | — | 39.7% | 19.6% | 87.6% | — | 13.1% | 0.3% | 开放 | 是 | 2025-11-27 |
| 331 | GLM-4.7-Flash (Non-reasoning)历史 | Z AI | 10.56* | — | — | — | — | — | 20.3% | 13.1% | 94.3% | — | 5% | 0% | 开放 | 否 | 2026-01-19 |
| 332 | Solar Open 100B | Upstage | 10.36* | — | — | — | — | — | 41% | 18.5% | 89.6% | — | 10.4% | 0% | 开放 | 是 | 2025-12-17 |
| 333 | Gemini 2.5 Flash-Lite (Sep)历史 | 10.35* | — | — | — | — | — | 64.7% | 18% | 87.8% | — | 7% | 0% | 闭源 | 是 | 2025-09-25 | |
| 334 | Nemotron 3 Nano Omni 30B A3B | NVIDIA | 10.25* | 415.52 裁判协议 v4.3.1 | — | — | — | — | 39.7% | 15.2% | 85.7% | — | 4.8% | 0% | 开放 | 是 | 2026-04-29 |
| 335 | gpt-oss-120b (low) | OpenAI | 10.21* | 364.46 裁判协议 v4.3.1 | — | — | — | — | 46% | 19.8% | 91.4% | — | 5.9% | 0% | 开放 | 是 | 2025-08-05 |
| 336 | GPT-4.1 mini历史 | OpenAI | 10.16* | 453.21 裁判协议 v4.3.1 | — | — | — | — | 44% | 20.3% | 92.7% | — | 5% | 0% | 闭源 | 否 | 2025-04-14 |
| 337 | Qwen3 Coder Next | Alibaba | 10.05 | 664.31 裁判协议 v4.3.1 | 413.75 裁判协议 v4.3.1 | 1.1% | 0% | 36.2% | 47% | 16.2% | 93.7% | 2.6% | 10.1% | 0% | 开放 | 否 | 2026-02-03 |
| 338 | Nova 2.0 Pro Preview (Non-reasoning) | Amazon | 9.96* | 508.59 裁判协议 v4.3.1 | — | — | — | — | 30% | 16.9% | 79.9% | — | 3.9% | 0% | 闭源 | 否 | 2025-11-27 |
| 339 | gpt-oss-20b (low) | OpenAI | 9.95* | — | — | — | — | — | 31% | 15.1% | 86.7% | — | 5.3% | 0% | 开放 | 是 | 2025-08-05 |
| 340 | Qwen3 VL 235B A22B历史 | Alibaba | 9.94* | — | — | — | — | — | 32.7% | 20.3% | 91.6% | — | 6.6% | 0% | 开放 | 否 | 2025-09-23 |
| 341 | North Mini Code | Cohere | 9.91 | 471.64 裁判协议 v4.3.1 | 234.19 裁判协议 v4.3.1 | 1.5% | 0.5% | 38.8% | 37.3% | 18.9% | 83.2% | 1.8% | 11.1% | 0.3% | 开放 | 是 | 2026-06-09 |
| 342 | GPT-5 mini (minimal)历史 | OpenAI | 9.91* | — | — | — | — | — | 39.3% | 19.2% | 89.3% | — | 5.1% | 0% | 闭源 | 否 | 2025-08-07 |
| 343 | K2-V2 (high) | Institute of Foundation Models | 9.87* | — | — | — | — | — | 35% | 18.5% | 91% | — | 10.5% | 0% | 开放 | 是 | 2025-12-05 |
| 344 | Gemini 2.5 Flash (Non-reasoning)历史 | 9.85* | — | — | — | — | — | 49.9% | 26.1% | 93% | — | 4.7% | 1.4% | 闭源 | 否 | 2025-05-20 | |
| 345 | Qwen3 30B A3B 2507历史 | Alibaba | 9.81 | 273.6 裁判协议 v4.3.1 | 31.59 裁判协议 v4.3.1 | 0.8% | 0% | 33% | 61.3% | 16.3% | 86.5% | 0.4% | 10.3% | 0.3% | 开放 | 是 | 2025-07-30 |
| 346 | DeepSeek V3 0324历史 | DeepSeek | 9.72 | 274.71 裁判协议 v4.3.1 | 91.96 裁判协议 v4.3.1 | 0.3% | 0% | 39% | 40.7% | 24.3% | 85.9% | 1.6% | 4.7% | 0% | 开放 | 否 | 2025-03-25 |
| 347 | Mistral Large 3 | Mistral | 9.71 | 588.39 裁判协议 v4.3.1 | 245.84 裁判协议 v4.3.1 | 1.5% | 0% | 36.6% | 36% | 24.9% | 86% | 1.2% | 4.2% | 0% | 开放 | 否 | 2025-12-02 |
| 348 | Ling 2.6 Flash历史 | InclusionAI | 9.68* | 492.76 裁判协议 v4.3.1 | — | — | — | — | 31.3% | 15.6% | 96.7% | — | 6.3% | 0% | 开放 | 否 | 2026-04-21 |
| 349 | Qwen3 Next 80B A3B | Alibaba | 9.64* | — | — | — | — | — | 52.7% | 17.3% | 92.7% | — | 7.6% | 0% | 开放 | 否 | 2025-09-11 |
| 350 | Tri-21B-think Preview历史 | Trillion Labs | 9.59* | — | — | — | — | — | 21.7% | 10.1% | 80.5% | — | 5.8% | 0% | 开放 | 是 | 2026-02-10 |
| 351 | Qwen3 Coder 30B A3B历史 | Alibaba | 9.59* | — | — | — | — | — | 32.7% | 16.4% | 80.3% | — | 3.8% | 0% | 开放 | 否 | 2025-07-31 |
| 352 | Mistral Medium 3.1历史 | Mistral | 9.53 | 536.15 裁判协议 v4.3.1 | 538.05 裁判协议 v4.3.1 | 4.1% | 0% | 32.4% | 42.7% | 20.8% | 84.6% | 1.2% | 4.7% | 0% | 闭源 | 否 | 2025-08-12 |
| 353 | DiffusionGemma 26B A4B | 9.51* | 501.29 裁判协议 v4.3.1 | — | — | — | — | 19.7% | 16.6% | 90.9% | — | 10.8% | 0.3% | 开放 | 是 | 2026-06-10 | |
| 354 | Qwen3 235B历史 | Alibaba | 9.5* | — | — | — | — | — | 0% | 18.5% | 77.6% | — | 11% | 0% | 开放 | 是 | 2025-04-28 |
| 355 | Qwen3 VL 30B A3B (Reasoning)历史 | Alibaba | 9.45* | — | — | — | — | — | — | 16.9% | 89.8% | — | 8.9% | 0% | 开放 | 是 | 2025-10-03 |
| 356 | Devstral 2 | Mistral | 9.41 | 688.65 裁判协议 v4.3.1 | 483.02 裁判协议 v4.3.1 | 3.1% | 0% | 32.8% | 32.3% | 20.8% | 85.3% | 2.4% | 3.6% | 0% | 开放 | 否 | 2025-12-09 |
| 357 | Gemma 4 12B (Non-reasoning) | 9.38* | — | — | — | — | — | 35% | 11.9% | 73.4% | — | 6.3% | 0% | 开放 | 否 | 2026-06-03 | |
| 358 | Gemini 2.5 Flash-Lite (Sep) (Non-reasoning)历史 | 9.34* | — | — | — | — | — | 49.7% | 14.1% | 66.1% | — | 5.1% | 0% | 闭源 | 否 | 2025-09-25 | |
| 359 | Llama 4 Maverick | Meta | 9.3 | -44.77 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.2% | 0% | 31.7% | 50% | 24.9% | 88.9% | 0.8% | 4.9% | 0% | 开放 | 否 | 2025-04-05 |
| 360 | Motif-2-12.7B | Motif Technologies | 9.19* | — | — | — | — | — | 14.7% | 15.2% | 90.6% | — | 8.8% | 0% | 闭源 | 是 | 2025-12-04 |
| 361 | Ling-1T历史 | InclusionAI | 9.17* | — | — | — | — | — | 36.7% | 20.3% | 94.7% | — | 7.3% | 0.6% | 开放 | 否 | 2025-10-08 |
| 362 | Nova Premier | Amazon | 9.16* | — | — | — | — | — | 34.3% | 21.3% | 71.9% | — | 4.2% | 0% | 闭源 | 否 | 2025-04-30 |
| 363 | Granite 4.2 3B | IBM | 9.06 | 389.62 裁判协议 v4.3.1 | 120.61 裁判协议 v4.3.1 | 0.4% | 0% | 25.3% | 24.3% | 9.2% | 26.3% | 0.2% | 6.6% | 0% | 开放 | 是 | 2026-08-25 |
| 364 | Magistral Medium 1历史 | Mistral | 9.05* | — | — | — | — | — | 0% | 20.3% | 59.3% | — | 9.8% | 0.3% | 闭源 | 是 | 2025-06-10 |
| 365 | Mistral Medium 3历史 | Mistral | 9.05* | — | — | — | — | — | 31.3% | 18.3% | 60.9% | — | 4% | 0% | 闭源 | 否 | 2025-05-07 |
| 366 | gpt-oss-20b (high) | OpenAI | 9.04 | 513.93 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.2% | 0% | 38.9% | 34.7% | 16% | 94.1% | 2% | 11% | 1.4% | 开放 | 是 | 2025-08-05 |
| 367 | K2-V2 (medium) | Institute of Foundation Models | 9.02* | — | — | — | — | — | 28% | 17.9% | 81.6% | — | 4.4% | 0% | 开放 | 是 | 2025-12-05 |
| 368 | Llama Nemotron Super 49B v1.5 | NVIDIA | 9.01* | — | — | — | — | — | — | 17.2% | 78.2% | — | 7.3% | 0% | 开放 | 是 | 2025-07-25 |
| 369 | Devstral Medium历史 | Mistral | 9.01* | — | — | — | — | — | 32% | 18.9% | 62.2% | — | 3.8% | 0% | 闭源 | 否 | 2025-07-10 |
| 370 | Mistral Small 4 (Non-reasoning) | Mistral | 8.99* | — | — | — | — | — | 28.3% | 16.6% | 78% | — | 3.8% | 0.3% | 开放 | 否 | 2026-03-16 |
| 371 | Tri-21B-Think | Trillion Labs | 8.99* | — | — | — | — | — | 15.7% | 12.3% | 85.4% | — | 5.9% | 0.3% | 开放 | 是 | 2026-02-10 |
| 372 | Gemini 2.0 Flash历史 | 8.94* | — | — | — | — | — | 31.3% | 23.5% | 86.2% | — | 4.3% | 0% | 闭源 | 否 | 2025-02-05 | |
| 373 | Claude 3.5 Haiku历史 | Anthropic | 8.94* | 407.74 裁判协议 v4.3.1 | — | — | — | — | 27.3% | 13.2% | 41.1% | — | 3.6% | 0% | 闭源 | 否 | 2024-10-22 |
| 374 | Llama 3.3 Nemotron Super 49B历史 | NVIDIA | 8.93* | — | — | — | — | — | 18.3% | 17.1% | 91% | — | 5.6% | 0% | 开放 | 是 | 2025-03-18 |
| 375 | Gemma 4 E4B | 8.91* | 176.92 裁判协议 v4.3.1 | — | — | — | — | 32% | 8.6% | 30.9% | — | 3.8% | 0.6% | 开放 | 是 | 2026-04-03 | |
| 376 | Nemotron 3 Nano | NVIDIA | 8.9 | 438.32 裁判协议 v4.3.1 | 100.39 裁判协议 v4.3.1 | 1% | 0% | 30.6% | 38% | 17.3% | 83.3% | 1% | 11.4% | 0.9% | 开放 | 是 | 2025-12-15 |
| 377 | Qwen3 4B 2507历史 | Alibaba | 8.8* | — | — | — | — | — | 37.3% | 12.5% | 83.2% | — | 6.2% | 0% | 开放 | 是 | 2025-08-06 |
| 378 | MiniCPM5-1B | OpenBMB | 8.8* | — | — | — | — | — | 6% | 2% | 17% | — | 6.5% | 0% | 开放 | 是 | 2026-05-25 |
| 379 | Sarvam 105B (high) | Sarvam | 8.79* | — | — | — | — | — | 0% | 17.6% | 93.4% | — | 11% | 0% | 开放 | 是 | 2026-03-06 |
| 380 | Nova 2.0 Lite (Non-reasoning) | Amazon | 8.74* | — | — | — | — | — | 18.7% | 14% | 85.9% | — | 2.9% | 0% | 闭源 | 否 | 2025-10-29 |
| 381 | Devstral Small (May)历史 | Mistral | 8.74* | — | — | — | — | — | 32% | 15.9% | 86.4% | — | 4% | 0% | 开放 | 否 | 2025-05-21 |
| 382 | MiniCPM5-1B (Non-reasoning) | OpenBMB | 8.69* | — | — | — | — | — | 5% | 0.1% | 0.9% | — | 4.5% | 0% | 开放 | 否 | 2026-05-25 |
| 383 | Magistral Small 1.2 | Mistral | 8.59* | 212.7 裁判协议 v4.3.1 | — | 0.2% | — | — | 19.3% | 13.5% | 90.8% | — | 6.4% | 0.3% | 开放 | 是 | 2025-09-17 |
| 384 | Gemini 2.5 Flash-Lite历史 | 8.55* | — | — | — | — | — | 55.7% | 17.9% | 77.4% | — | 6.8% | 0% | 闭源 | 是 | 2025-06-17 | |
| 385 | DeepSeek V3 (Dec)历史 | DeepSeek | 8.49 | 183.26 裁判协议 v4.3.1 | 99.91 裁判协议 v4.3.1 | 0.6% | 0% | 35.8% | 29.3% | 25.4% | 90% | 0.8% | 2.9% | 0% | 开放 | 否 | 2024-12-26 |
| 386 | GPT-4o (Nov)历史 | OpenAI | 8.44* | — | — | — | — | — | 49.3% | 19.9% | 37.9% | — | 2.4% | 0% | 闭源 | 否 | 2024-11-20 |
| 387 | Nanbeige4.1-3B | Nanbeige | 8.4* | -166.42 裁判协议 v4.3.1 | — | — | — | — | 0% | 9.9% | 58.1% | — | 10.9% | 0% | 开放 | 是 | 2026-02-11 |
| 388 | LFM2.5-2.6B | Liquid AI | 8.39* | 202.35 裁判协议 v4.3.1 | — | — | — | 14.4% | 5.7% | 4.3% | 16% | — | 6.2% | 0% | 开放 | 是 | 2026-08-04 |
| 389 | Qwen3 VL 32B历史 | Alibaba | 8.39* | — | — | — | — | — | — | 14.8% | 91.8% | — | 6.8% | 0% | 开放 | 否 | 2025-10-21 |
| 390 | Devstral Small 2 | Mistral | 8.36 | 679.88 裁判协议 v4.3.1 | 495.98 裁判协议 v4.3.1 | 3.1% | 0% | 32.4% | 28% | 15.8% | 87.3% | 1% | 3.5% | 0% | 开放 | 否 | 2025-12-09 |
| 391 | GLM-4.6V (Non-reasoning)历史 | Z AI | 8.35* | — | — | — | — | — | 17% | 17.4% | 66.6% | — | 3.7% | 0% | 开放 | 否 | 2025-12-08 |
| 392 | Qwen3 235B (Non-reasoning)历史 | Alibaba | 8.29* | — | — | — | — | — | 0% | 18.6% | 87.1% | — | 4.2% | 0% | 开放 | 否 | 2025-04-28 |
| 393 | Magistral Small 1历史 | Mistral | 8.22* | — | — | — | — | — | 0% | 18% | 76.1% | — | 7.6% | 0% | 开放 | 是 | 2025-06-10 |
| 394 | EXAONE 4.0 32B | LG AI Research | 8.18* | — | — | — | — | — | — | 13.9% | 85.8% | — | 11.4% | 0% | 开放 | 是 | 2025-07-15 |
| 395 | Qwen3 VL 8B (Reasoning)历史 | Alibaba | 8.17* | — | — | — | — | — | 33.3% | 20.4% | 91.4% | — | 3.8% | 0.3% | 开放 | 是 | 2025-10-14 |
| 396 | Nova 2.0 Omni (Non-reasoning) | Amazon | 8.15* | — | — | — | — | — | 24.7% | 13.2% | 89.3% | — | 3.8% | 0% | 闭源 | 否 | 2025-11-26 |
| 397 | DeepSeek R1 0528 Qwen3 8B历史 | DeepSeek | 8.08* | — | — | — | — | — | 15% | 12.2% | 86.4% | — | 5.9% | 0% | 开放 | 是 | 2025-05-29 |
| 398 | Qwen3 VL 30B A3B历史 | Alibaba | 7.93* | — | — | — | — | — | — | 15.6% | 93.7% | — | 6.3% | 0% | 开放 | 否 | 2025-10-03 |
| 399 | Hermes 4 70B | Nous Research | 7.91* | — | — | — | — | — | 9.7% | 23.5% | 95.4% | — | 8.8% | 0% | 开放 | 是 | 2025-08-27 |
| 400 | DeepSeek R1 Distill Llama 70B历史 | DeepSeek | 7.89* | — | — | — | — | — | 10% | 19.2% | 81.1% | — | 5.1% | 0% | 开放 | 是 | 2025-01-20 |
| 401 | Falcon-H1R-7B | TII UAE | 7.83* | — | — | — | — | — | 11% | 14.5% | 88.8% | — | 11% | 0.3% | 开放 | 是 | 2026-01-04 |
| 402 | GPT-4.1 nano历史 | OpenAI | 7.82* | 12.78 裁判协议 v4.3.1 | — | — | — | — | 20.3% | 13.7% | 82.6% | — | 3.8% | 0% | 闭源 | 否 | 2025-04-14 |
| 403 | Solar Pro 3历史 | Upstage | 7.82 | 446.94 裁判协议 v4.3.1 | 121.9 裁判协议 v4.3.1 | 0.5% | 0% | 25.5% | 32.3% | 18.5% | 88.2% | 1.6% | 10.3% | 0% | 闭源 | 是 | 2026-04-06 |
| 404 | Ling-flash-2.0历史 | InclusionAI | 7.81* | — | — | — | — | — | 17.7% | 14.1% | 89.5% | — | 6.2% | 0% | 开放 | 否 | 2025-09-17 |
| 405 | Gemma 4 E2B | 7.77* | 36.05 裁判协议 v4.3.1 | — | — | — | — | 16.3% | 6.6% | 32.4% | — | 4.8% | 0% | 开放 | 是 | 2026-04-02 | |
| 406 | Qwen3 Omni 30B A3B (Reasoning) | Alibaba | 7.76* | — | — | — | — | — | 0% | 14.6% | 89% | — | 7.5% | 0% | 开放 | 是 | 2025-09-22 |
| 407 | GPT-4o (Aug)历史 | OpenAI | 7.74* | — | — | — | — | — | 41% | 23.7% | 58.4% | — | 2.3% | 0% | 闭源 | 否 | 2024-08-06 |
| 408 | Qwen2.5 72B历史 | Alibaba | 7.73* | — | — | — | — | — | — | 17.5% | 85.5% | — | 3.6% | 0% | 开放 | 否 | 2024-09-19 |
| 409 | Step3 VL 10B | StepFun | 7.69* | — | — | — | — | — | 0% | 13.3% | 83.3% | — | 10.8% | 0% | 开放 | 是 | 2026-01-20 |
| 410 | Llama 3.3 70B | Meta | 7.66* | 49.51 裁判协议 v4.3.1 | — | — | — | — | 15.7% | 18.9% | 90.2% | — | 3.6% | 0% | 开放 | 否 | 2024-12-06 |
| 411 | Qwen3 30B历史 | Alibaba | 7.63* | — | — | — | — | — | 0% | 16.2% | 80.7% | — | 6.2% | 0% | 开放 | 是 | 2025-04-28 |
| 412 | Devstral Small历史 | Mistral | 7.6* | — | — | — | — | — | 18.7% | 14.7% | 76.9% | — | 3.8% | 0% | 开放 | 否 | 2025-07-10 |
| 413 | GLM-4.5V历史 | Z AI | 7.56* | — | — | — | — | — | 0% | 20.8% | 84.8% | — | 6.3% | 0% | 开放 | 是 | 2025-08-11 |
| 414 | Mistral Large 2 (Nov)历史 | Mistral | 7.56* | — | — | — | — | — | — | 19.9% | 67.7% | — | 3.3% | 0% | 开放 | 否 | 2024-11-18 |
| 415 | Llama Nemotron Ultra | NVIDIA | 7.53* | — | — | — | — | — | — | 20.1% | 81.2% | — | 7.4% | 0% | 开放 | 是 | 2025-04-07 |
| 416 | Qwen3 30B A3B 2507 (Non-reasoning)历史 | Alibaba | 7.52* | — | — | — | — | — | 26.3% | 15% | 95.4% | — | 6.9% | 0% | 开放 | 否 | 2025-07-29 |
| 417 | ERNIE 4.5 300B A47B | Baidu | 7.5* | — | — | — | — | — | — | 19.1% | 66.9% | — | 3.3% | 0% | 开放 | 否 | 2025-06-30 |
| 418 | Hermes 4 405B | Nous Research | 7.49* | — | — | — | — | — | 22.3% | 30.1% | 94.5% | — | 10.9% | 0.3% | 开放 | 是 | 2025-08-27 |
| 419 | Solar Pro 2历史 | Upstage | 7.49* | — | — | — | — | — | 0% | 20% | 94.7% | — | 7.4% | 0% | 闭源 | 是 | 2025-07-09 |
| 420 | NVIDIA Nemotron Nano 12B v2 VL | NVIDIA | 7.48* | — | — | — | — | — | 41% | 14.6% | 92.3% | — | 5.5% | 0% | 开放 | 是 | 2025-10-28 |
| 421 | Gemma 4 E4B (Non-reasoning) | 7.46* | — | — | — | — | — | 24% | 8.3% | 53.8% | — | 4.8% | 0.3% | 开放 | 否 | 2026-04-03 | |
| 422 | Granite 4.1 30B历史 | IBM | 7.44* | 378.65 裁判协议 v4.3.1 | — | — | — | — | 23.7% | 14% | 95% | — | 4.1% | 0% | 开放 | 否 | 2026-04-29 |
| 423 | NVIDIA Nemotron Nano 9B V2 | NVIDIA | 7.43* | — | — | — | — | — | 22.7% | 11.8% | 60.5% | — | 4.9% | 0% | 开放 | 是 | 2025-08-18 |
| 424 | Hermes 4 405B (Non-reasoning) | Nous Research | 7.41* | — | — | — | — | — | 22% | 26.1% | 80.2% | — | 4.2% | 0% | 开放 | 否 | 2025-08-27 |
| 425 | Nemotron 3 Nano 4B | NVIDIA | 7.38* | 159.11 裁判协议 v4.3.1 | — | — | — | — | 21.7% | 9.6% | 88.6% | — | 4.9% | 0% | 开放 | 是 | 2026-03-16 |
| 426 | Mistral Small 3.1历史 | Mistral | 7.37 | 549.93 裁判协议 v4.3.1 | 324.58 裁判协议 v4.3.1 | 1.2% | 0% | 27.8% | 22.3% | 15.1% | 77.6% | 1% | 4.3% | 0% | 开放 | 否 | 2025-03-17 |
| 427 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | 7.36* | — | — | — | — | — | 24.7% | 12.6% | 67.3% | — | 4.3% | 0% | 开放 | 否 | 2025-07-25 |
| 428 | K2-V2 (low) | Institute of Foundation Models | 7.31* | — | — | — | — | — | 20.3% | 16.3% | 76% | — | 3.6% | 0% | 开放 | 是 | 2025-12-05 |
| 429 | Llama 3.1 405B | Meta | 7.29* | — | — | — | — | — | 25.3% | 23.2% | 52.4% | — | 4% | 0% | 开放 | 否 | 2024-07-23 |
| 430 | Llama 3.3 Nemotron Super 49B (Non-reasoning)历史 | NVIDIA | 7.28* | — | — | — | — | — | 12% | 13.5% | 73.7% | — | 3.8% | 0% | 开放 | 否 | 2025-03-18 |
| 431 | Qwen3 VL 8B历史 | Alibaba | 7.26* | — | — | — | — | — | 16.7% | 20.5% | 91% | — | 2.7% | 0% | 开放 | 否 | 2025-10-14 |
| 432 | LFM2.5-8B-A1B | Liquid AI | 7.22* | — | — | — | — | — | 0% | 9.3% | 46.9% | — | 6.9% | 0% | 开放 | 是 | 2026-05-28 |
| 433 | Qwen3 32B历史 | Alibaba | 7.22 | 239.65 裁判协议 v4.3.1 | 9.49 裁判协议 v4.3.1 | 1% | 0% | 36% | 0% | 17.4% | 82.1% | 1.6% | 7.4% | 0.3% | 开放 | 是 | 2025-04-28 |
| 434 | Ring-flash-2.0 | InclusionAI | 7.15* | — | — | — | — | — | 21% | 16.6% | 90.1% | — | 9.6% | 0.3% | 开放 | 是 | 2025-09-19 |
| 435 | Olmo 3.1 32B Think | Allen Institute for AI | 7.12* | — | — | — | — | — | 0% | 13.8% | 66.3% | — | 6.3% | 0% | 开放 | 是 | 2025-12-12 |
| 436 | GPT-5 nano (minimal)历史 | OpenAI | 7.09* | — | — | — | — | — | 20% | 13.1% | 88.8% | — | 4% | 0% | 闭源 | 否 | 2025-08-07 |
| 437 | Qwen3 VL 4B (Reasoning)历史 | Alibaba | 7.05* | — | — | — | — | — | 21.3% | 12.2% | 91.8% | — | 4.6% | 0% | 开放 | 是 | 2025-10-14 |
| 438 | Solar Pro 2 (Non-reasoning)历史 | Upstage | 7* | — | — | — | — | — | 0% | 16.1% | 93% | — | 3.7% | 0% | 闭源 | 否 | 2025-07-09 |
| 439 | Mistral Small 3.2历史 | Mistral | 6.96 | 29.2 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.3% | 0% | 28.6% | 20.3% | 14.8% | 76.8% | 0% | 4.3% | 0% | 开放 | 否 | 2025-06-20 |
| 440 | Nova Pro历史 | Amazon | 6.96* | — | — | — | — | — | 21% | 16.9% | 77.7% | — | 3.2% | 0% | 闭源 | 否 | 2024-12-03 |
| 441 | Command A | Cohere | 6.96* | — | — | — | — | — | 21.3% | 16.4% | 77.3% | — | 4% | 0% | 开放 | 否 | 2025-03-13 |
| 442 | Qwen3.5 2B | Alibaba | 6.94* | 165.7 裁判协议 v4.3.1 | — | — | — | — | 21% | 8.1% | 74.2% | — | 2.6% | 0% | 开放 | 是 | 2026-03-02 |
| 443 | Llama 3.1 Nemotron 70B | NVIDIA | 6.94* | — | — | — | — | — | 8.3% | 17.8% | 71.3% | — | 4.2% | 0% | 开放 | 否 | 2024-10-15 |
| 444 | Llama 3.1 8B历史 | Meta | 6.93* | -150.78 裁判协议 v4.3.1 | — | — | — | — | 18% | 8.5% | 43% | — | 5.3% | 0% | 开放 | 否 | 2024-07-23 |
| 445 | Nemotron 3 Nano (Non-reasoning) | NVIDIA | 6.85* | -121.8 裁判协议 v4.3.1 | — | — | — | — | 10.7% | 11.4% | 91% | — | 4.6% | 0% | 开放 | 否 | 2025-12-15 |
| 446 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | 6.84* | — | — | — | — | — | 24% | 9.8% | 74.4% | — | 4.6% | 0% | 开放 | 否 | 2025-08-18 |
| 447 | Qwen3 4B 2507 (Non-reasoning)历史 | Alibaba | 6.74* | — | — | — | — | — | 11.3% | 10.9% | 81.7% | — | 4.5% | 0% | 开放 | 否 | 2025-08-06 |
| 448 | Qwen3 14B (Non-reasoning)历史 | Alibaba | 6.7* | — | — | — | — | — | 0% | 13.3% | 92.3% | — | 4.1% | 0% | 开放 | 否 | 2025-04-28 |
| 449 | GPT-4历史 | OpenAI | 6.7* | 188.72 裁判协议 v4.3.1 | — | — | — | — | — | 21% | 69.4% | — | — | — | 闭源 | 否 | 2023-03-14 |
| 450 | GLM-4.5V (Non-reasoning)历史 | Z AI | 6.7* | — | — | — | — | — | 0% | 18.2% | 90.2% | — | 3.5% | 0% | 开放 | 否 | 2025-08-11 |
| 451 | Gemini 2.5 Flash-Lite (Non-reasoning)历史 | 6.67* | — | — | — | — | — | 32% | 15.4% | 87.8% | — | 3.7% | 0% | 闭源 | 否 | 2025-06-17 | |
| 452 | Nova Lite历史 | Amazon | 6.67* | — | — | — | — | — | 19% | 9.8% | 57.6% | — | 4.3% | 0% | 闭源 | 否 | 2024-12-03 |
| 453 | Hermes 4 70B (Non-reasoning) | Nous Research | 6.66* | — | — | — | — | — | 4.7% | 18.7% | 82.7% | — | 3.6% | 0% | 开放 | 否 | 2025-08-27 |
| 454 | Qwen3 30B (Non-reasoning)历史 | Alibaba | 6.62* | — | — | — | — | — | 0% | 12% | 88.5% | — | 4.6% | 0% | 开放 | 否 | 2025-04-28 |
| 455 | Llama 3.1 70B历史 | Meta | 6.6* | — | — | — | — | — | — | 19.7% | 78.2% | — | 4.5% | 0% | 开放 | 否 | 2024-07-23 |
| 456 | Granite 4.1 8B历史 | IBM | 6.57* | — | — | — | — | — | 13.3% | 12.3% | 87.1% | — | 3.8% | 0% | 开放 | 否 | 2026-04-29 |
| 457 | Sarvam 30B (high) | Sarvam | 6.56* | — | — | — | — | — | 0% | 12.6% | 96.3% | — | 7.5% | 0.3% | 开放 | 是 | 2026-03-06 |
| 458 | Olmo 3.1 32B Instruct | Allen Institute for AI | 6.5* | — | — | — | — | — | 0% | 12% | 73.2% | — | 5% | 0% | 开放 | 否 | 2026-01-13 |
| 459 | Gemma 4 E2B (Non-reasoning) | 6.48* | — | — | — | — | — | 16.3% | 8.2% | 74.4% | — | 4.7% | 0% | 开放 | 否 | 2026-04-02 | |
| 460 | Olmo 3 32B Think历史 | Allen Institute for AI | 6.47* | — | — | — | — | — | 0% | 14.9% | 85.7% | — | 6.4% | 0% | 开放 | 是 | 2025-11-20 |
| 461 | Llama 4 Scout | Meta | 6.45 | 59.71 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.2% | 0% | 21.3% | 27.7% | 15.2% | 79.4% | 0% | 3.8% | 0% | 开放 | 否 | 2025-04-05 |
| 462 | Qwen3 14B历史 | Alibaba | 6.39 | 187.72 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.2% | 0% | 30.7% | 0% | 15.3% | 75.8% | 1.2% | 4.5% | 0% | 开放 | 是 | 2025-04-28 |
| 463 | Celeris-1 | Celeris | 6.35 | 482.83 裁判协议 v4.3.1 | 171.51 裁判协议 v4.3.1 | 0.4% | 0% | 21.6% | 38% | 11% | 92.8% | 1.2% | 6.8% | 0% | 闭源 | 否 | 2026-07-24 |
| 464 | Phi-4 Mini | Microsoft | 6.33* | -171.32 裁判协议 v4.3.1 | — | — | — | — | 15.3% | 9.5% | 78% | — | 4.5% | 0% | 开放 | 否 | 2024-02-26 |
| 465 | EXAONE 4.0 32B (Non-reasoning) | LG AI Research | 6.33* | — | — | — | — | — | — | 10.6% | 82.1% | — | 5% | 0% | 开放 | 否 | 2025-07-15 |
| 466 | Qwen3.5 2B (Non-reasoning) | Alibaba | 6.19* | -130.44 裁判协议 v4.3.1 | — | — | — | — | 14% | 7.4% | 97.7% | — | 5% | 0% | 开放 | 否 | 2026-03-02 |
| 467 | Qwen3.5 0.8B | Alibaba | 6.13* | -152.17 裁判协议 v4.3.1 | — | — | — | — | 9% | 4.2% | 61.3% | — | 1.1% | 0% | 开放 | 是 | 2026-03-02 |
| 468 | Jamba 1.7 Large | AI21 Labs | 6.07* | — | — | — | — | — | 19.3% | 20.6% | 95.1% | — | 3.7% | 0% | 开放 | 否 | 2025-07-07 |
| 469 | Granite 4.0 H Small | IBM | 6.05* | — | — | — | — | — | 11.3% | 14.3% | 87.8% | — | 3.8% | 0% | 开放 | 否 | 2025-09-22 |
| 470 | Ministral 3 14B | Mistral | 6.04 | 432.06 裁判协议 v4.3.1 | 149.57 裁判协议 v4.3.1 | 0.6% | 0% | 23.8% | 26.3% | 13.6% | 92.5% | 1.2% | 4.6% | 0% | 开放 | 否 | 2025-12-02 |
| 471 | Qwen3 Omni 30B A3B | Alibaba | 6.01* | — | — | — | — | — | 0% | 14.3% | 97.6% | — | 4.6% | 0% | 开放 | 否 | 2025-09-22 |
| 472 | Qwen3 8B (Non-reasoning)历史 | Alibaba | 5.99* | — | — | — | — | — | 0% | 11.1% | 95.6% | — | 1.9% | 0% | 开放 | 否 | 2025-04-28 |
| 473 | LFM2 24B A2B | Liquid AI | 5.95* | — | — | — | — | — | 0% | 6.5% | 69% | — | 4.2% | 0% | 开放 | 否 | 2026-02-25 |
| 474 | Phi-4 | Microsoft | 5.92* | — | — | — | — | — | 0% | 14.1% | 81.2% | — | 3.8% | 0% | 开放 | 否 | 2024-12-12 |
| 475 | Nova Micro | Amazon | 5.88* | — | — | — | — | — | 13% | 10% | 65.1% | — | 4.6% | 0% | 闭源 | 否 | 2024-12-03 |
| 476 | Granite 4.1 3B历史 | IBM | 5.86* | 73.87 裁判协议 v4.3.1 | — | — | — | — | 6% | 9.3% | 95.1% | — | 3.4% | 0% | 开放 | 否 | 2026-04-29 |
| 477 | NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | NVIDIA | 5.82* | — | — | — | — | — | 20.7% | 11.9% | 95.5% | — | 4.3% | 0% | 开放 | 否 | 2025-10-28 |
| 478 | MiniCPM-V 4.6 1.3B | OpenBMB | 5.69* | -134.2 裁判协议 v4.3.1 | — | — | — | — | 7% | 6.7% | 96.1% | — | 5.1% | 0% | 开放 | 否 | 2026-05-11 |
| 479 | Jamba Reasoning 3B | AI21 Labs | 5.67* | — | — | — | — | — | 6.3% | 6.7% | 69% | — | 3.8% | 0% | 开放 | 是 | 2025-10-08 |
| 480 | Qwen3 VL 4B历史 | Alibaba | 5.66* | — | — | — | — | — | 14% | 10.9% | 97.4% | — | 3.6% | 0% | 开放 | 否 | 2025-10-14 |
| 481 | Reka Flash 3 | Reka AI | 5.65* | — | — | — | — | — | 0% | 13.7% | 91.3% | — | 4.4% | 0% | 开放 | 是 | 2025-03-10 |
| 482 | Olmo 3 7B Think | Allen Institute for AI | 5.62* | — | — | — | — | — | 0% | 11.1% | 93.2% | — | 6% | 0% | 开放 | 是 | 2025-11-20 |
| 483 | Claude 3 Haiku历史 | Anthropic | 5.58* | — | — | — | — | — | 27.7% | 17.6% | 80.5% | — | 4.1% | 0% | 闭源 | 否 | 2024-03-04 |
| 484 | Ling-mini-2.0历史 | InclusionAI | 5.54* | — | — | — | — | — | — | 8.9% | 95.9% | — | 5.1% | 0% | 开放 | 否 | 2025-09-09 |
| 485 | Ministral 3 8B | Mistral | 5.48 | 404.6 裁判协议 v4.3.1 | 99.22 裁判协议 v4.3.1 | 0.5% | 0% | 20.7% | 25.7% | 13% | 94.2% | 0.8% | 4.3% | 0% | 开放 | 否 | 2025-12-02 |
| 486 | Llama 3 70B历史 | Meta | 5.45* | — | — | — | — | — | 0% | 17.7% | 87.5% | — | 4.5% | 0% | 开放 | 否 | 2024-04-18 |
| 487 | Llama 3.2 11B (Vision) | Meta | 5.41* | — | — | — | — | — | 12.7% | 10.6% | 81.9% | — | 5.5% | 0% | 开放 | 否 | 2024-09-25 |
| 488 | Qwen3.5 0.8B (Non-reasoning) | Alibaba | 5.4* | -133.2 裁判协议 v4.3.1 | — | — | — | — | 8% | 5% | 98.5% | — | 5.1% | 0% | 开放 | 否 | 2026-03-02 |
| 489 | Sarvam M历史 | Sarvam | 5.31* | — | — | — | — | — | 0% | 15.2% | 90.6% | — | 3.1% | 0% | 开放 | 是 | 2025-05-23 |
| 490 | Exaone 4.0 1.2B | LG AI Research | 5.27* | — | — | — | — | — | 0% | 6.8% | 93% | — | 6% | 0% | 开放 | 是 | 2025-07-15 |
| 491 | Olmo 3 7B | Allen Institute for AI | 5.24* | — | — | — | — | — | 0% | 7.4% | 91.2% | — | 5.8% | 0% | 开放 | 否 | 2025-11-20 |
| 492 | Exaone 4.0 1.2B (Non-reasoning) | LG AI Research | 5.23* | — | — | — | — | — | 0% | 5% | 91.7% | — | 5.7% | 0% | 开放 | 否 | 2025-07-15 |
| 493 | LFM2.5-1.2B-Thinking | Liquid AI | 5.22* | — | — | — | — | — | 0% | 7.4% | 94.4% | — | 6.2% | 0% | 开放 | 是 | 2026-01-20 |
| 494 | Jamba 1.7 Mini | AI21 Labs | 5.22* | — | — | — | — | — | 16% | 11.3% | 95.1% | — | 4.4% | 0% | 开放 | 否 | 2025-07-07 |
| 495 | LFM2 2.6B历史 | Liquid AI | 5.21* | — | — | — | — | — | 0% | 5.4% | 62.9% | — | 5.5% | 0% | 开放 | 否 | 2025-09-23 |
| 496 | LFM2.5-1.2B-Instruct | Liquid AI | 5.21* | — | — | — | — | — | 0% | 7% | 85.1% | — | 6.7% | 0% | 开放 | 否 | 2026-01-05 |
| 497 | Granite 4.0 H 1B | IBM | 5.19* | — | — | — | — | — | 7% | 5.2% | 81.7% | — | 5% | 0% | 开放 | 否 | 2025-10-28 |
| 498 | Qwen3 1.7B历史 | Alibaba | 5.19* | — | — | — | — | — | 0% | 8.9% | 94.8% | — | 4.6% | 0% | 开放 | 是 | 2025-04-28 |
| 499 | Qwen3 8B历史 | Alibaba | 5.16 | 165.39 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.3% | 0% | 27.9% | 0% | 13.6% | 90.7% | 1.4% | 3.9% | 0% | 开放 | 是 | 2025-04-28 |
| 500 | Gemma 3 270M | 5.12* | — | — | — | — | — | 0% | 0.9% | 30.4% | — | 3.6% | 0% | 开放 | 否 | 2025-08-14 | |
| 501 | Apertus 70B Instruct | Swiss AI Initiative | 5.11* | — | — | — | — | — | 0% | 11.6% | 82.8% | — | 5.5% | 0% | 开放 | 否 | 2025-09-02 |
| 502 | Granite 4.0 Micro | IBM | 5.11* | — | — | — | — | — | 7% | 9.3% | 95.8% | — | 5% | 0% | 开放 | 否 | 2025-09-22 |
| 503 | Mistral 7B历史 | Mistral | 5.03* | — | — | — | — | — | 0% | 9% | 81.3% | — | 4.5% | 0% | 开放 | 否 | 2023-09-27 |
| 504 | Granite 4.0 1B历史 | IBM | 5.01* | — | — | — | — | — | 6% | 6.2% | 93.5% | — | 4.8% | 0% | 开放 | 否 | 2025-10-28 |
| 505 | Molmo2-8B | Allen Institute for AI | 5* | — | — | — | — | — | 0% | 11.5% | 91.1% | — | 4.3% | 0% | 开放 | 否 | 2025-12-11 |
| 506 | LFM2 8B A1B历史 | Liquid AI | 4.93* | — | — | — | — | — | — | 8.2% | 92.3% | — | 4.9% | 0% | 开放 | 否 | 2025-10-07 |
| 507 | Granite 3.3 8B历史 | IBM | 4.92* | — | — | — | — | — | — | 9.7% | 96.2% | — | 4.2% | 0% | 开放 | 否 | 2025-04-16 |
| 508 | Qwen3 1.7B (Non-reasoning)历史 | Alibaba | 4.86* | — | — | — | — | — | 0% | 6.9% | 97.8% | — | 5.3% | 0% | 开放 | 否 | 2025-04-28 |
| 509 | Gemma 3 27B历史 | 4.85 | -171.05 裁判协议 v4.3.1 | — | 0.2% | 0% | 23.3% | 7.3% | 13% | 92.1% | 0.2% | 4.4% | 0% | 开放 | 否 | 2025-03-12 | |
| 510 | Ministral 3 3B | Mistral | 4.84 | 233.97 裁判协议 v4.3.1 | 16.01 裁判协议 v4.3.1 | 0.7% | 0% | 15.3% | 17% | 9% | 80.2% | 0% | 5.4% | 0% | 开放 | 否 | 2025-12-02 |
| 511 | Qwen3 0.6B (Non-reasoning)历史 | Alibaba | 4.83* | — | — | — | — | — | 0% | 4.6% | 93.8% | — | 4.9% | 0% | 开放 | 否 | 2025-04-28 |
| 512 | LFM2 1.2B历史 | Liquid AI | 4.83* | — | — | — | — | — | 0% | 4.9% | 81.4% | — | 5.6% | 0% | 开放 | 否 | 2025-07-10 |
| 513 | Gemma 3 4B历史 | 4.83* | — | — | — | — | — | 6.7% | 7.7% | 98.2% | — | 5.3% | 0% | 开放 | 否 | 2025-03-12 | |
| 514 | LFM2.5-VL-1.6B | Liquid AI | 4.83* | — | — | — | — | — | 0% | 5.8% | 95.7% | — | 5.1% | 0% | 开放 | 否 | 2026-01-05 |
| 515 | Qwen3 0.6B历史 | Alibaba | 4.83* | — | — | — | — | — | 0% | 6.3% | 90.9% | — | 5.6% | 0% | 开放 | 是 | 2025-04-28 |
| 516 | Granite 4.0 350M | IBM | 4.83* | — | — | — | — | — | 0% | 3.9% | 76.1% | — | 5.5% | 0% | 开放 | 否 | 2025-10-28 |
| 517 | Llama 3.2 1B历史 | Meta | 4.83* | — | — | — | — | — | 6.7% | 7% | 66.3% | — | 5.5% | 0% | 开放 | 否 | 2024-09-25 |
| 518 | Tiny Aya Global | Cohere | 4.83* | — | — | — | — | — | 0% | 6.1% | 96.2% | — | 5.2% | 0% | 开放 | 否 | 2026-02-17 |
| 519 | Llama 3 8B历史 | Meta | 4.83* | — | — | — | — | — | 0% | 10.4% | 89.8% | — | 5.1% | 0% | 开放 | 否 | 2024-04-18 |
| 520 | Apertus 8B Instruct | Swiss AI Initiative | 4.83* | — | — | — | — | — | 0% | 9.7% | 96.1% | — | 5% | 0% | 开放 | 否 | 2025-09-02 |
| 521 | Granite 4.0 H 350M | IBM | 4.83* | — | — | — | — | — | 0% | 3.8% | 88.1% | — | 6.4% | 0% | 开放 | 否 | 2025-10-28 |
| 522 | Gemma 3n E4B历史 | 4.83* | — | — | — | — | — | 0% | 8% | 97.1% | — | 4.5% | 0% | 开放 | 否 | 2025-06-26 | |
| 523 | Gemma 3n E2B历史 | 4.83* | — | — | — | — | — | 0% | 6.8% | 93.4% | — | 4.2% | 0% | 开放 | 否 | 2025-06-26 | |
| 524 | Gemma 3 1B历史 | 4.83* | — | — | — | — | — | 0% | 3.8% | 82.3% | — | 5.3% | 0% | 开放 | 否 | 2025-03-13 | |
| 525 | Gemma 3 12B历史 | 3.75 | -169.68 裁判协议 v4.3.1 | — | 0.2% | 0% | 16.4% | 8.3% | 10.3% | 97.4% | 1% | 4.2% | 0% | 开放 | 否 | 2025-03-12 | |
| 526 | K2 Horizon 0.9B | Institute of Foundation Models | 3.05 | -173.76 裁判协议 v4.3.1 | 0 裁判协议 v4.3.1 | 0.2% | 0% | 6.9% | 6.3% | 6.9% | 85.7% | 0.8% | 5.4% | 0% | 开放 | 是 | 2026-09-03 |
| 527 | Mi:dm K 2.5 Pro Preview历史 | Korea Telecom | — | — | — | — | — | — | 14.7% | 16.4% | 94.7% | — | 9.1% | 0% | 闭源 | 是 | 2025-12-11 |
| 528 | Cogito v2.1 | Deep Cogito | — | — | — | — | — | — | 22.7% | 30.2% | 80.2% | — | 12% | 0% | 开放 | 是 | 2025-11-18 |
旧版包含 9 项评测:GDPval-AA v2、τ³-Banking、Terminal-Bench v2.1、SciCode、AA-LCR、AA-Omniscience、Humanity's Last Exam、GPQA Diamond、CritPt。v4.3 引入新的组成项、任务版本与权重,不能把换版本后的分数差直接解释成模型进步或退步。
查看当前权重与旧版方法对照 →AA-Briefcase 与 GDPval-AA v2 的当前成对比较使用裁判协议 v4.3.1,原评测名称与任务版本不变,Intelligence Index 仍为 v4.3。未区分裁判协议的旧 Elo 保留原始观测,仅作历史参考,不与当前协议混排。
指数中的 Elo 贡献在模型加入时冻结;实时榜单分数不能用于重算指数。来源未给出逐模型重跑日期,不能把裁判更新或跨协议分数差解释成新的模型运行或能力变化。
查看裁判、核验时间与完整方法边界 →查看 AA 原始方法 ↗FAQ
回答只使用来源页面可以明确核对的指标定义。
包含 AA-Briefcase、GDPval-AA v2、AutomationBench-AA、Terminal-Bench v4.0、SciCode、AA-Omniscience、GDP.pdf、AA-LCR v1.1、Humanity's Last Exam 和 CritPt,共 10 项;Omniscience 的准确率与非幻觉率分别计入权重。
不可以直接把跨版本分数差解释成能力变化。两版的任务集、组成评测和权重不同;本站按版本展示,旧观测保留 v4.1 身份,新观测不覆盖旧历史。
估算是 Artificial Analysis 对该结果的标记,不等同于全部组成评测均已完成。本站保留估算标记与原始分数,缺失组成字段显示为未知,不自行补算。
不是。该方法补丁更新 AA-Briefcase 与 GDPval-AA v2 的实时 Elo 成对裁判,Intelligence Index 仍标为 v4.3;指数中的 Elo 贡献在模型加入时冻结,不能用实时 Elo 重算。旧观测未区分裁判协议时仅作历史参考。
按方法版本拆解知识、推理、编程、工具使用和长上下文表现,不混排不同版本。
评测结果受任务集合、评分方法和模型版本影响。本站保留原始口径,不用它生成新的综合排名。
用于回答一个明确的问题:模型在这一类任务上的相对表现如何,而不是“哪个模型绝对最好”。