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 ↓.
316/316
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） |
|---|---|---|---|---|---|---|---|
| #72 | GPT-5.2 Chat none | OpenAI | 7.3 | 7.9 | $0.594 | 1/2 | 13.9s |
| #73 | Step 3.7 Flash medium | Stepfun | 7.3 | 7.9 | $0.495 | 1/2 | 80.9s |
| #75 | Qwen3.7 Plus medium | Qwen | 8.2 | 7.9 | $0.277 | 1/2 | 190.3s |
| #77 | Gemini 3.5 Flash Lite medium | 7.3 | 7.8 | $0.272 | 1/2 | 17.9s | |
| #81 | Qwen3.8 27B medium | Qwen | 8.7 | 7.8 | ~$0.058 | 1/2 | 124.5s |
| #82 | Seed-2.0-Lite medium | Bytedance Seed | 6.4 | 7.8 | $0.236 | 1/2 | 58.5s |
| #84 | Qwen3.7 Flash high | Qwen | 6.9 | 7.8 | $0.052 | 1/2 | 232.0s |
| #86 | Seed-2.0-Code low | Bytedance Seed | 7.3 | 7.7 | $0.767 | 1/2 | 99.1s |
| #89 | DeepSeek V4 Flash 0423 high | DeepSeek | 6.4 | 7.6 | $0.042 | 1/2 | 104.1s |
| #93 | Nemotron 3 Ultra medium | NVIDIA | 6.3 | 7.6 | $0.701 | 1/2 | 218.2s |
| #94 | Claude Opus 5 none | Anthropic | 8.3 | 7.5 | $1.550 | 1/2 | 30.5s |
| #96 | GPT-5.6 Terra low | OpenAI | 8.7 | 7.5 | $0.420 | 1/2 | 9.68s |
| #99 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 6.9 | 7.5 | $0.459 | 1/2 | 175.8s |
| #100 | Qwen3.5-27B medium | Qwen | 7.3 | 7.5 | $0.982 | 1/2 | 595.2s |
| #101 | Mercury 2.5 Preview medium | Inception | 6.5 | 7.5 | $0.024 | 1/2 | 13.9s |