93.8综合分
数据快照 · 2026/10/1
86.6综合分
90.3综合分
每个模型展示本项最高实测分,展开查看其他档位。33 个模型 · 81 个配置
ⓘ
排序方式与筛选条件
质量优先更看重得分;得分与耗时平衡兼顾两者;评测耗时优先更看重任务完成时间。每款模型展示当前偏好下的实测档位。
这里使用的是评测任务耗时,不代表日常对话的响应速度。
| 排名 | 模型 / 实测档位 | 后端 | 前端 | 知识推理 | 评测用时 | 参考费用 | 对比 | |
|---|---|---|---|---|---|---|---|---|
| 01 | 95.5 | 97 | 94 | 95 | 93m 26s | $8.35 | ||
| 02 | 93.8 | 95 | 96 | 90 | 62m 9s | $1.69 | ||
| 03 | 90.3 | 84 | 89 | 100 | 33m 57s | $3.67 | ||
| 04 | 89.8 | 85 | 91 | 95 | 79m 7s | $26.15 | ||
| 05 | 86.6 | 86 | 89 | 85 | 48m 32s | $2.80 | ||
| 06 | 84.3 | 87 | 80 | 85 | 196m 18s | $5.25 | ||
| 07 | 82.7 | 80 | 94 | 75 | 39m 22s | $1.10 | ||
| 08 | 82.6 | 70 | 87 | 95 | 92m 12s | $7.99 | ||
| 09 | 80.7 | 78 | 80 | 85 | 144m 16s | $2.51 | ||
| 10 | 78.4 | 85 | 73 | 75 | 87m 21s | $3.25 | ||
| 11 | 77.5 | 61 | 87 | 90 | 102m 10s | $9.18 | ||
| 12 | k3新 | 74.5 | 70 | 85 | 70 | 158m 17s | $3.28 | |
| 13 | 73.0 | 70 | 85 | 65 | 336m 3s | $0.66 | ||
| 14 | 71.7 | 81 | 76 | 55 | 133m 2s | $1.94 | ||
| 15 | 71.0 | 74 | 73 | 65 | 218m 41s | $1.63 | ||
| 16 | 70.9 | 61 | 80 | 75 | 62m 35s | $0.000 | ||
| 17 | 70.7 | 62 | 88 | 65 | 35m 40s | $0.41 | ||
| 18 | 70.4 | 65 | 78 | 70 | 157m 1s | $1.83 | ||
| 19 | 69.6 | 75 | 57 | 75 | 54m 7s | 暂无暂无费用 | ||
| 20 | 68.3 | 68 | 87 | 50 | 134m 31s | $0.42 | ||
| 21 | 68.2 | 61 | 71 | 75 | 98m 22s | $1.24 | ||
| 22 | 65.2 | 67 | 63 | 65 | 93m 15s | $1.15 | ||
| 23 | 64.2 | 54 | 72 | 70 | 70m 58s | $0.66 | ||
| 24 | 63.8 | 62 | 80 | 50 | 63m 52s | $0.061 | ||
| 25 | 63.4 | 64 | 86 | 40 | 25m 21s | $0.13费用未齐 | ||
| 26 | 62.5 | 58 | 76 | 55 | 98m 25s | $0.42 | ||
| 27 | 58.3 | 61 | 43 | 70 | 88m 43s | $0.32 | ||
| 27 | 58.3 | 64 | 69 | 40 | 133m 3s | $3.41费用未齐 | ||
| 29 | 58.0 | 58 | 71 | 45 | 386m 14s | $0.28 | ||
| 30 | 56.9 | 65 | 78 | 25 | 86m 14s | $0.35 | ||
| 31 | 56.1 | 54 | 75 | 40 | 100m 0s | $0.078费用未齐 | ||
| 32 | 54.0 | 63 | 71 | 25 | 24m 19s | $0.13 | ||
| 33 | 52.9 | 46 | 65 | 50 | 56m 33s | $0.62费用未齐 |
各模型采用本项最高分档位;同分并列。
后端 40% · 前端 30% · 推理 30%,采用同一实测配置。 评测范围与数据来源 →

