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) |
|---|---|---|---|---|---|---|---|
| #359 | GPT-5.4 none | OpenAI | 0.5 | 0.6 | $0.690 | 0/1 | 43.7s |
| #277 | Beam 1.0 501B A23B xhigh | Reflection | 0.3 | 0.6 | $0.688 | 0/1 | 44.6s |
| #416 | Mimo V2 Omni medium | Xiaomi | 0.0 | 0.5 | $0.683 | 0/0 | 0ms |
| #205 | Gemini 2.5 Flash medium | 0.3 | 0.7 | $0.680 | 0/1 | 6.54s | |
| #150 | Nemotron 3 Ultra medium | NVIDIA | 1.0 | 0.8 | $0.674 | 1/1 | 188.1s |
| #320 | Beam 1.0 501B A23B high | Reflection | 0.3 | 0.6 | $0.674 | 0/1 | 33.5s |
| #67 | Gemini 4 Argon medium | 1.0 | 0.9 | $0.674 | 1/1 | 62.5s | |
| #314 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 0.3 | 0.6 | $0.669 | 0/1 | 3.38s |
| #38 | Gemini 4 Hydrogen low | 1.0 | 0.9 | $0.669 | 1/1 | 46.6s | |
| #329 | Claude Sonnet 4.6 none | Anthropic | 0.0 | 0.6 | $0.661 | 0/0 | 0ms |
| #267 | LongCat 2.0 low | Meituan | 0.6 | 0.7 | $0.630 | 0/1 | 145.6s |
| #66 | Gemini 3.5 Flash Lite high | 1.0 | 0.9 | $0.624 | 1/1 | 53.1s | |
| #156 | GLM 5.3 FlashX max | Z.ai | 0.6 | 0.8 | $0.623 | 0/1 | 104.8s |
| #84 | DeepSeek V4.1 Flash high | DeepSeek | 1.0 | 0.9 | $0.617 | 1/1 | 44.0s |
| #72 | Muse Spark Open low | Meta | 1.0 | 0.9 | $0.600 | 1/1 | 55.0s |