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 ↓.
504/504
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) |
|---|---|---|---|---|---|---|---|
| #31 | Claude Opus 5 high | Anthropic | 1.0 | 0.9 | $4.524 | 1/1 | 87.0s |
| #32 | Claude Opus 5 medium | Anthropic | 1.0 | 0.9 | $2.870 | 1/1 | 78.8s |
| #33 | GPT-6.1 Terra xhigh | OpenAI | 1.0 | 0.9 | $0.789 | 1/1 | 47.9s |
| #34 | GPT-6.1 Terra low | OpenAI | 1.0 | 0.9 | $0.221 | 1/1 | 43.5s |
| #35 | Seed 2.1 Turbo low | Bytedance Seed | 1.0 | 0.9 | $1.645 | 1/1 | 102.8s |
| #36 | Gemini 4 Hydrogen medium | 1.0 | 0.9 | $1.330 | 1/1 | 70.4s | |
| #37 | Muse Ember high | Meta | 1.0 | 0.9 | $0.156 | 1/1 | 48.3s |
| #38 | Gemini 4 Hydrogen low | 1.0 | 0.9 | $0.669 | 1/1 | 46.6s | |
| #39 | Gemini 4 Carbon high | 1.0 | 0.9 | $6.107 | 1/1 | 242.7s | |
| #40 | Muse Spark Open high | Meta | 1.0 | 0.9 | $1.782 | 1/1 | 50.1s |
| #41 | Claude Opus 5.5 medium | Anthropic | 1.0 | 0.9 | $1.804 | 1/1 | 62.6s |
| #42 | Muse Wonder medium | Meta | 1.0 | 0.9 | $3.397 | 1/1 | 46.0s |
| #43 | GPT-5.5 medium | OpenAI | 1.0 | 0.9 | $4.809 | 1/1 | 59.4s |
| #44 | Claude Sonnet 5.5 max | Anthropic | 1.0 | 0.9 | $8.557 | 1/1 | 111.1s |
| #45 | Qwen3.8 MAX medium | Qwen | 1.0 | 0.9 | $1.181 | 1/1 | 115.3s |