智能体任务 排名
看看哪些 AI 模型在 智能体任务 上表现最好，哪些更稳定，以及差距主要出现在哪里。 排序方式: 测试正确 ↑.
380/380
筛选模型
没有模型匹配当前搜索和筛选条件。
| 排名 | 模型 | 公司 | 智能体任务 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #280 | Granite 4.2 8B low | IBM Granite | 6.1 | 5.3 | $0.036 | 0/1 | 142.7s |
| #281 | Kimi K2.5 none | Moonshot AI | 5.0 | 5.3 | $0.236 | 0/1 | 321.2s |
| #282 | Qwen3.6 Max Preview none | Qwen | 0.0 | 5.3 | $0.228 | 0/0 | 0ms |
| #283 | Laguna XS 2.1 none | Poolside | 5.0 | 5.3 | $0.019 | 0/1 | 70.8s |
| #284 | Qwen3.6 35B A3B none | Qwen | 5.2 | 5.3 | $0.105 | 0/1 | 65.6s |
| #285 | Inkling Small low | Thinkingmachines | 3.0 | 5.2 | $0.059 | 0/1 | 24ms |
| #286 | Ling 3.0 Flash none | Inclusionai | 3.0 | 5.2 | $0.000 | 0/1 | 26ms |
| #287 | Nemotron 3.5 Lightning high | NVIDIA | 3.5 | 5.2 | $0.111 | 0/1 | 491.0s |
| #288 | KAT Coder AIR V2.5 high | Kwaipilot | 3.0 | 5.2 | $0.077 | 0/1 | 1.10s |
| #289 | Mimo V2 PRO medium | Xiaomi | 0.0 | 5.2 | $0.333 | 0/0 | 0ms |
| #290 | MiMo-V2-Flash medium | Xiaomi | 0.0 | 5.1 | $0.043 | 0/0 | 0ms |
| #291 | Mistral Small 4 medium | Mistral | 5.0 | 5.1 | $0.126 | 0/1 | 54.1s |
| #292 | Mistral Small 4 none | Mistral | 5.0 | 5.1 | $0.047 | 0/1 | 45.5s |
| #293 | Mercury 2.5 low | Inception | 5.0 | 5.1 | $0.020 | 0/1 | 47.1s |
| #294 | KAT Coder AIR V2.5 medium | Kwaipilot | 3.0 | 5.1 | $0.048 | 0/1 | 1.05s |