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: 总成本 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #275 | MiMo-V2.6-Flash none | Xiaomi | 5.0 | 5.4 | $0.060 | 0/1 | 62.6s |
| #285 | Inkling Small low | Thinkingmachines | 3.0 | 5.2 | $0.059 | 0/1 | 24ms |
| #303 | Inkling Small none | Thinkingmachines | 3.0 | 4.9 | $0.058 | 0/1 | 31ms |
| #362 | Grok 4.20 none | X AI | 0.0 | 3.4 | $0.057 | 0/0 | 0ms |
| #279 | GPT-5.6 Luna none | OpenAI | 5.0 | 5.3 | $0.056 | 0/1 | 53.8s |
| #89 | DeepSeek V4 Flash 0423 high | DeepSeek | 10.0 | 8.1 | $0.056 | 1/1 | 148.1s |
| #228 | DeepSeek V4 Flash 0731 none | DeepSeek | 10.0 | 6.2 | $0.055 | 1/1 | 174.9s |
| #114 | Qwen3.7 Flash low | Qwen | 10.0 | 7.7 | $0.053 | 1/1 | 106.7s |
| #184 | GLM 5.3 Flash low | Z.ai | 10.0 | 6.6 | $0.052 | 1/1 | 59.7s |
| #323 | GLM 5V Turbo none | Z.ai | 0.0 | 4.6 | $0.052 | 0/0 | 0ms |
| #223 | DeepSeek V4 Flash 0423 none | DeepSeek | 10.0 | 6.3 | $0.050 | 1/1 | 92.9s |
| #278 | Hy3 preview medium | Tencent | 0.0 | 5.3 | $0.049 | 0/0 | 0ms |
| #294 | KAT Coder AIR V2.5 medium | Kwaipilot | 3.0 | 5.1 | $0.048 | 0/1 | 1.05s |
| #336 | Granite 4.2 8B none | IBM Granite | 5.0 | 4.4 | $0.047 | 0/1 | 49.2s |
| #79 | GPT-6 Luna medium | OpenAI | 10.0 | 8.3 | $0.047 | 1/1 | 66.4s |