谜题求解 排名
看看哪些 AI 模型在 谜题求解 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 ↑.
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 | 谜题求解 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #322 | Seed-2.0-Code none | Bytedance Seed | 0.8 | 0.5 | $0.257 | 2/3 | 10.0s |
| #108 | DeepSeek V4 Flash 0423 high | DeepSeek | 0.8 | 0.8 | $0.261 | 2/3 | 26.1s |
| #333 | Kimi K2.5 none | Moonshot AI | 0.3 | 0.5 | $0.262 | 0/3 | 4.04s |
| #104 | Seed-2.0-Lite medium | Bytedance Seed | 0.9 | 0.8 | $0.271 | 2/3 | 10.2s |
| #18 | Gemini 3.7 Flash medium | 1.0 | 1.0 | $0.278 | 3/3 | 2.33s | |
| #141 | Muse Glimmer 30B medium | Meta | 0.6 | 0.8 | $0.288 | 1/3 | 64.7s |
| #304 | Mistral Large 4 none | Mistral | 0.8 | 0.6 | $0.290 | 2/3 | 19.3s |
| #277 | Inkling none | Thinkingmachines | 0.6 | 0.6 | $0.292 | 1/3 | 931ms |
| #203 | Inkling low | Thinkingmachines | 0.6 | 0.7 | $0.293 | 1/3 | 2.97s |
| #67 | Qwen3.8 27B high | Qwen | 0.8 | 0.9 | ~$0.298 | 2/3 | 199.9s |
| #153 | DeepSeek V4 Flash 0731 low | DeepSeek | 0.8 | 0.7 | $0.306 | 2/3 | 9.08s |
| #238 | Qwen3.5-122B-A10B none | Qwen | 0.4 | 0.6 | $0.308 | 0/3 | 1.00s |
| #84 | GPT-5 Mini medium | OpenAI | 0.6 | 0.8 | $0.315 | 1/3 | 15.2s |
| #171 | Gemini 3.8 Flash low | 1.0 | 0.7 | $0.323 | 3/3 | 2.25s | |
| #269 | GLM 5 Turbo medium | Z.ai | 0.9 | 0.6 | $0.323 | 2/3 | 5.23s |