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） |
|---|---|---|---|---|---|---|---|
| #97 | GLM 5.3 FlashX max | Z.ai | 6.1 | 7.9 | $0.623 | 0/1 | 104.8s |
| #98 | Claude Fable 5.1 high | Anthropic | 3.0 | 7.9 | $3.471 | 0/1 | 6.93s |
| #102 | Grok 4.5 medium | X AI | 5.0 | 7.8 | $2.454 | 0/1 | 65.2s |
| #104 | Step 3.7 Flash medium | Stepfun | 7.4 | 7.8 | $0.571 | 0/1 | 93.9s |
| #105 | Grok 4.6 medium | X AI | 5.0 | 7.8 | $2.270 | 0/1 | 103.6s |
| #106 | GPT-6 Luna medium | OpenAI | 7.4 | 7.8 | $0.048 | 0/1 | 71.7s |
| #108 | Grok 4.5 low | X AI | 5.0 | 7.8 | $1.345 | 0/1 | 61.5s |
| #110 | GPT-6 Luna high | OpenAI | 5.2 | 7.7 | $0.074 | 0/1 | 82.8s |
| #116 | Qwen3.8 27B low | Qwen | 6.1 | 7.6 | ~$0.089 | 0/1 | 211.3s |
| #121 | GPT-5.4 Mini medium | OpenAI | 7.4 | 7.4 | $0.965 | 0/1 | 84.3s |
| #122 | GPT-5.6 Luna medium | OpenAI | 7.4 | 7.4 | $0.101 | 0/1 | 58.1s |
| #124 | DeepSeek V4 Flash 0731 low | DeepSeek | 4.7 | 7.4 | $0.307 | 0/1 | 321.2s |
| #127 | Grok 4.7 low | X AI | 5.0 | 7.4 | $2.263 | 0/1 | 154.9s |
| #128 | Inkling Small high | Thinkingmachines | 3.0 | 7.4 | $0.402 | 0/1 | 23ms |
| #130 | Inkling medium | Thinkingmachines | 4.7 | 7.4 | $0.540 | 0/1 | 45.9s |