编程 排名
看看哪些 AI 模型在 编程 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: 指标 ↑.
226/226
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 | 编程 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #11 | Claude Opus 5 high | Anthropic | 10.0 | 9.2 | $2.835 | 3/3 | 12.7s |
| #12 | Claude Opus 5 medium | Anthropic | 10.0 | 9.2 | $1.486 | 3/3 | 9.56s |
| #13 | Qwen3.7 Max medium | Qwen | 10.0 | 9.2 | $1.116 | 3/3 | 35.3s |
| #17 | Grok 4.5 high | X AI | 10.0 | 8.9 | $1.707 | 3/3 | 155.2s |
| #18 | GPT-5.3-Codex medium | OpenAI | 10.0 | 8.9 | $0.920 | 3/3 | 19.5s |
| #19 | Claude Opus 4.8 medium | Anthropic | 10.0 | 8.8 | $1.931 | 3/3 | 15.3s |
| #21 | Muse Spark 1.1 medium | Meta | 10.0 | 8.6 | $1.357 | 3/3 | 15.7s |
| #22 | Claude Fable 5 medium | Anthropic | 10.0 | 8.6 | $3.478 | 3/3 | 15.6s |
| #26 | Grok 4.5 low | X AI | 10.0 | 8.4 | $0.935 | 3/3 | 13.7s |
| #27 | GPT-5.2 medium | OpenAI | 10.0 | 8.4 | $0.951 | 3/3 | 22.7s |
| #30 | Muse Spark 1.1 low | Meta | 10.0 | 8.3 | $0.647 | 3/3 | 10.3s |
| #32 | GPT-5 Mini medium | OpenAI | 10.0 | 8.1 | $0.237 | 3/3 | 27.6s |
| #33 | Muse Spark 1.1 high | Meta | 10.0 | 8.1 | $1.694 | 3/3 | 22.9s |
| #40 | Kimi K3 max | Moonshot AI | 10.0 | 8.0 | $3.112 | 3/3 | 325.8s |
| #49 | GLM 5 medium | Z.ai | 10.0 | 7.7 | $0.307 | 3/3 | 74.3s |