综合 排名
看看哪些 AI 模型在 综合 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 ↓.
455/455
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 | 综合 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #82 | Nemotron 3.5 Super VL high | NVIDIA | 0.7 | 0.8 | $0.349 | 1/2 | 183.5s |
| #344 | Mimo V2 PRO medium | Xiaomi | 0.2 | 0.5 | $0.333 | 0/1 | 64.7s |
| #248 | MiMo-V2.5-Pro medium | Xiaomi | 0.7 | 0.6 | $0.332 | 1/2 | 125.4s |
| #354 | MiniMax M2.7 medium | Minimax | 0.4 | 0.5 | $0.326 | 0/2 | 72.1s |
| #269 | GLM 5 Turbo medium | Z.ai | 0.5 | 0.6 | $0.323 | 1/1 | 13.9s |
| #171 | Gemini 3.8 Flash low | 0.4 | 0.7 | $0.323 | 0/2 | 19.6s | |
| #84 | GPT-5 Mini medium | OpenAI | 0.7 | 0.8 | $0.315 | 1/2 | 99.8s |
| #238 | Qwen3.5-122B-A10B none | Qwen | 0.5 | 0.6 | $0.308 | 0/2 | 129.3s |
| #153 | DeepSeek V4 Flash 0731 low | DeepSeek | 1.0 | 0.7 | $0.306 | 2/2 | 54.2s |
| #67 | Qwen3.8 27B high | Qwen | 1.0 | 0.9 | ~$0.298 | 2/2 | 185.6s |
| #203 | Inkling low | Thinkingmachines | 0.3 | 0.7 | $0.293 | 0/2 | 22.7s |
| #279 | Inkling none | Thinkingmachines | 0.3 | 0.6 | $0.292 | 0/2 | 25.7s |
| #306 | Mistral Large 4 none | Mistral | 0.3 | 0.6 | $0.290 | 0/2 | 36.9s |
| #141 | Muse Glimmer 30B medium | Meta | 0.7 | 0.8 | $0.288 | 1/2 | 76.5s |
| #18 | Gemini 3.7 Flash medium | 1.0 | 1.0 | $0.278 | 2/2 | 20.9s |