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） |
|---|---|---|---|---|---|---|---|
| #102 | Grok 4.5 medium | X AI | 5.0 | 7.8 | $2.454 | 0/1 | 65.2s |
| #164 | Ember-1 high | Fireworks | 6.1 | 6.9 | $2.405 | 0/1 | 88.3s |
| #39 | Claude Opus 5 low | Anthropic | 10.0 | 9.0 | $2.350 | 1/1 | 73.2s |
| #162 | Claude Opus 4.8 none | Anthropic | 5.4 | 6.9 | $2.328 | 0/1 | 69.1s |
| #339 | Gemini 3.1 Flash Lite Preview high | 0.0 | 4.3 | $2.310 | 0/0 | 0ms | |
| #105 | Grok 4.6 medium | X AI | 5.0 | 7.8 | $2.270 | 0/1 | 103.6s |
| #127 | Grok 4.7 low | X AI | 5.0 | 7.4 | $2.263 | 0/1 | 154.9s |
| #14 | GPT-6 Astra low | OpenAI | 10.0 | 9.6 | $2.160 | 1/1 | 49.2s |
| #24 | Claude Opus 5.5 high | Anthropic | 10.0 | 9.4 | $2.133 | 1/1 | 64.4s |
| #205 | Claude Sonnet 4.6 medium | Anthropic | 0.0 | 6.4 | $2.126 | 0/0 | 0ms |
| #65 | Qwen3.7 Max medium | Qwen | 6.1 | 8.5 | $2.046 | 0/1 | 137.0s |
| #322 | Gemini 3.1 Flash Lite high | 0.0 | 4.6 | $2.044 | 0/0 | 0ms | |
| #56 | Seed 2.1 Turbo medium | Bytedance Seed | 10.0 | 8.7 | $2.042 | 1/1 | 90.9s |
| #42 | Muse Spark 1.2 high | Meta | 10.0 | 8.9 | $2.018 | 1/1 | 62.5s |
| #48 | GPT-5.4 medium | OpenAI | 10.0 | 8.8 | $2.006 | 1/1 | 67.8s |