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 ↓.
514/514
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) |
|---|---|---|---|---|---|---|---|
| #278 | GLM 5.3 low | Z.ai | 0.5 | 0.6 | $0.215 | 0/1 | 48.8s |
| #196 | GLM 5.3 FlashX high | Z.ai | 1.0 | 0.7 | $0.210 | 1/1 | 78.0s |
| #224 | MiMo-V2.6-Flash low | Xiaomi | 0.5 | 0.7 | $0.200 | 0/1 | 107.9s |
| #221 | Qwen3.8 Flash Next xhigh | Qwen | 0.5 | 0.7 | ~$0.195 | 0/1 | 173.7s |
| #420 | Nemotron 3.5 Lightning medium | NVIDIA | 0.3 | 0.5 | $0.195 | 0/1 | 341.8s |
| #446 | GLM 4.7 Flash medium | Z.ai | 0.4 | 0.4 | $0.193 | 0/1 | 399.2s |
| #332 | MiMo-V2.6-Pro none | Xiaomi | 0.5 | 0.6 | $0.193 | 0/1 | 66.1s |
| #109 | Muse Ember medium | Meta | 1.0 | 0.9 | $0.190 | 1/1 | 47.2s |
| #246 | Qwen3.5-Flash medium | Qwen | 1.0 | 0.7 | $0.184 | 1/1 | 67.7s |
| #100 | GPT-6.1 Terra none | OpenAI | 1.0 | 0.9 | $0.184 | 1/1 | 40.3s |
| #300 | Gemini 3.5 Flash Lite low | 0.5 | 0.6 | $0.183 | 0/1 | 53.9s | |
| #30 | Gemini 3.7 Flash low | 1.0 | 0.9 | $0.183 | 1/1 | 58.8s | |
| #354 | Seed 2.1 Turbo none | Bytedance Seed | 0.5 | 0.6 | $0.182 | 0/1 | 71.4s |
| #172 | Qwen3.7 Plus none | Qwen | 1.0 | 0.8 | $0.178 | 1/1 | 143.1s |
| #210 | Nex-N2.6 high | NEX AGI | 0.6 | 0.7 | $0.177 | 0/1 | 111.9s |