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: 测试正确 ↑.
451/451
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） |
|---|---|---|---|---|---|---|---|
| #311 | Step 5 Preview low | Stepfun | 0.7 | 0.6 | $4.110 | 1/2 | 40.9s |
| #315 | Nemotron 3 Super medium | NVIDIA | 0.6 | 0.6 | $0.081 | 1/2 | 259.9s |
| #328 | Step 3.5 Flash medium | Stepfun | 0.7 | 0.5 | $0.105 | 1/2 | 813.7s |
| #334 | Qwen3.6 Max Preview none | Qwen | 0.7 | 0.5 | $0.228 | 1/2 | 61.6s |
| #339 | Nemotron 3.5 Lightning high | NVIDIA | 0.6 | 0.5 | $0.168 | 1/2 | 160.5s |
| #340 | KAT Coder AIR V2.5 high | Kwaipilot | 0.7 | 0.5 | $0.077 | 1/2 | 74.5s |
| #346 | KAT Coder AIR V2.5 medium | Kwaipilot | 0.7 | 0.5 | $0.048 | 1/2 | 19.6s |
| #354 | KAT Coder AIR V2.5 low | Kwaipilot | 0.6 | 0.5 | $0.046 | 1/2 | 55.9s |
| #356 | Inkling Small none | Thinkingmachines | 0.7 | 0.5 | $0.054 | 1/2 | 9.33s |
| #360 | Ling 2.6 1t default | Inclusionai | 0.7 | 0.5 | $0.016 | 1/2 | 23.8s |
| #368 | Nemotron 3.5 Lightning medium | NVIDIA | 0.6 | 0.5 | $0.195 | 1/2 | 136.9s |
| #378 | Nemotron 3.5 Lightning low | NVIDIA | 0.6 | 0.5 | $0.175 | 1/2 | 142.4s |
| #1 | Gemini 3.6 Flash high | 1.0 | 1.0 | $0.900 | 2/2 | 65.1s | |
| #2 | Gemini 3.8 Flash high | 1.0 | 1.0 | $1.927 | 2/2 | 115.7s | |
| #3 | GPT-6 Sol high | OpenAI | 1.0 | 1.0 | $0.921 | 2/2 | 30.4s |