HyperAI
Command Palette
Search for a command to run...
FrontierCode-AA 2.0
Cognition FrontierCode 2.0 的实现,这是一个私有智能体编程基准,包含真实开源仓库中的 132 个任务,以维护者是否会合并智能体的改动作为评分标准。
- 类别
- 编程
- 智能指数权重
- 15%
- 模型
- 107 当前,123 总共
- 中位数
- 20.2%
- 范围
- 0.0%–49.1%
| 排名 | 比较 | 模型 | 评分 | 成本 / 任务 | 时间 / 任务 | 输出 token / 任务 |
|---|---|---|---|---|---|---|
| 1 | 49.1% | $9.64 | 18m 45s | 105K | ||
| 2 | 48.8% | $43.37 | 68m 6s | 420K | ||
| 3 | 47.6% | $21.41 | 35m 25s | 219K | ||
| 4 | 46.4% | $13.46 | 28m 31s | 200K | ||
| 5 | 43.8% | $6.49 | 15m 38s | 102K | ||
| 6 | GPT-6 Astra (Max) OpenAI | 42.4% | $6.54 | 16m 26s | 37.1K | |
| 7 | GPT-6.1 Terra (Max) OpenAI | 42.3% | $1.29 | 15m 29s | 68.1K | |
| 8 | 41.7% | $11.56 | 34m 17s | 316K | ||
| 9 | GPT-6 Astra (Xhigh) OpenAI | 41.4% | $4.04 | 8m 44s | 20.4K | |
| 10 | 41.3% | $2.69 | 5m 49s | 31.7K | ||
| 11 | GPT-6.1 Sol (Max) OpenAI | 40.6% | $1.13 | 11m 47s | 39.7K | |
| 12 | Gemini 4 Carbon (High) Google | 40.6% | $12.02 | 25m 55s | 128K | |
| 13 | GPT-6 Astra (High) OpenAI | 40.1% | $3.77 | 8m 4s | 19K | |
| 14 | Gemini 4 Carbon (Medium) Google | 39.5% | $10.07 | 24m 55s | 110K | |
| 15 | GPT-6.1 Sol (Xhigh) OpenAI | 38.5% | $0.70 | 6m 32s | 21.9K | |
| 16 | 38.4% | $2.12 | 4m 35s | 25.5K | ||
| 17 | 37.8% | — | — | 72.7K | ||
| 18 | GPT-6.1 Terra (High) OpenAI | 37.5% | $0.39 | 4m 54s | 20.6K | |
| 19 | GPT-6.1 Terra (Xhigh) OpenAI | 36.9% | $0.57 | 6m 51s | 29.5K | |
| 20 | GPT-6.1 Sol (High) OpenAI | 36.7% | $0.63 | 5m 41s | 19.4K | |
| 21 | GPT-6 Astra (Medium) OpenAI | 36.6% | $2.80 | 5m 16s | 13.5K | |
| 22 | 35.9% | $2.49 | 6m 48s | 42.7K | ||
| 23 | 35.6% | $2.71 | 10m 15s | 85.4K | ||
| 24 | Claude Haiku 5.5 (Max) Anthropic | 34.9% | $0.46 | 16m 43s | 255K | |
| 25 | GPT-6.1 Terra (Medium) OpenAI | 34.5% | $0.26 | 3m 17s | 13.7K | |
| 26 | GPT-6.1 Sol (Medium) OpenAI | 33.4% | $0.41 | 3m 32s | 12.5K | |
| 27 | 33.4% | $0.43 | 3m 27s | 14.3K | ||
| 28 | 33.1% | $1.71 | 5m 1s | 31K | ||
| 29 | Tencent Hy4 Tencent | 31.4% | $1.39 | — | 79.7K | |
| 30 | Claude Haiku 5.5 (Xhigh) Anthropic | 29.9% | $0.26 | 10m 24s | 148K | |
| 31 | Gemini 4 Carbon (Low) Google | 29.6% | $13.19 | 13m 55s | 53.8K | |
| 32 | Grok 4.7 (Xhigh) SpaceXAI | 28.7% | $13.83 | 30m 47s | 118K | |
| 33 | DeepSeek V4.1 Flash 1017 (Max) DeepSeek | 28.5% | $0.52 | 14m 1s | 116K | |
| 34 | 27.9% | $5.04 | 8m 56s | 65.4K | ||
| 35 | Grok 4.7 (High) SpaceXAI | 27.8% | $11.06 | 24m 44s | 99.9K | |
| 36 | Muse Ember (Max) Meta | 27.2% | $0.096 | 1m 59s | 54.2K | |
| 37 | 26.6% | $3.04 | 5m 59s | 43.5K | ||
| 38 | GPT-6 Astra (Low) OpenAI | 26.2% | $1.34 | 2m 51s | 6.8K | |
| 39 | 25.7% | $0.76 | 3m 16s | 27.6K | ||
| 40 | Gemini 4 Argon (High) Google | 25.7% | $18.74 | 38m 26s | 156K | |
| 41 | Kimi K3.1 Pro Kimi | 25.5% | $2.38 | 21m 50s | 42.5K | |
| 42 | Inkling 2 Small Thinking Machines | 25.4% | $1.26 | 17m 12s | 132K | |
| 43 | GPT-6 Luna (Max) OpenAI | 25.2% | $0.18 | 10m 39s | 69.8K | |
| 44 | GPT-6.1 Terra (Low) OpenAI | 24.5% | $0.11 | 1m 28s | 5.98K | |
| 45 | MiMo-V2.6-Pro Xiaomi | 24.0% | $0.26 | 34m 24s | 116K | |
| 46 | Qwen3.8 Max (0902) Alibaba | 23.4% | $6.71 | 39m 50s | 122K | |
| 47 | Claude Haiku 5.5 (High) Anthropic | 23.2% | $0.14 | 6m 6s | 83.4K | |
| 48 | 22.0% | $0.076 | 1m 38s | 44.7K | ||
| 49 | MiniMax-M3 MiniMax | 21.9% | $1.29 | 13m 51s | 103K | |
| 50 | Grok 4.7 (Low) SpaceXAI | 21.8% | $4.33 | 11m 3s | 42.8K |