HyperAI
Command Palette
Search for a command to run...
Terminal-Bench 4.0
소프트웨어, 머신러닝, 과학, 운영, 보안, 하드웨어, 미디어 전반의 복잡한 터미널 작업 66개로 구성된 더 어려운 벤치마크로, 컴퓨트와 시간 허용량을 재조정하고 지침, 환경, 검증기를 개선했습니다.
- 카테고리
- 코딩
- 지능 지수 가중치
- 10%
- 모델
- 147 현재, 252 전체
- 중앙값
- 11.1%
- 범위
- 0.0%–67.2%
| 순위 | 비교 | 모델 | 점수 | 비용 / 작업 | 시간 / 작업 | 출력 토큰 / 작업 |
|---|---|---|---|---|---|---|
| 101 |  Hy3 Tencent | 0.5% | — | — | — | |
| 102 | 0.5% | $0.30 | 8m 14s | 44.3K | ||
| 103 |  Nemotron 3.5 Lightning NVIDIA | 0.5% | $0.34 | 5m 49s | 84.9K | |
| 104 |  North Mini Code Cohere | 0.5% | $0 | 4m 19s | 44K | |
| 105 | 0.5% | $1.71 | 4m 33s | 51.6K | ||
| 106 |  Qwen3.5 9B (Reasoning) Alibaba | 0.5% | — | — | — | |
| 107 |  Ring-2.6-1T InclusionAI | 0.5% | — | — | — | |
| 108 |  Trinity Large Thinking Arcee AI | 0.5% | — | — | — | |
| 109 |  A.X-K2 SK Telecom | 0.0% | — | — | — | |
| 110 |  Apodex 1.1 Apodex | 0.0% | $2.05 | 27m 25s | 234K | |
| 111 |  Celeris-1 Celeris | 0.0% | — | — | — | |
| 112 |  Gemma 4 31B (Reasoning) Google | 0.0% | — | — | — | |
| 113 | Gemma 4 E4B (Reasoning) Google | 0.0% | — | — | — | |
| 114 |  GPT-6 Luna (Low) OpenAI | 0.0% | $0.0054 | 42.7s | 3.7K | |
| 115 | gpt-oss-120b (High) OpenAI | 0.0% | $0.064 | 2m 7s | 20.6K | |
| 116 | gpt-oss-20b (High) OpenAI | 0.0% | — | — | — | |
| 117 | 0.0% | — | — | — | ||
| 118 | 0.0% | — | — | 43.2K | ||
| 119 | 0.0% | $0.04 | 8m 51s | 51.2K | ||
| 120 |  HyperNova 60B 2605 (High, Based on gpt-oss-120b) Multiverse Computing | 0.0% | — | — | — | |
| 121 |  K-EXAONE 2.0 LG AI Research | 0.0% | — | — | 90.9K | |
| 122 |  K2 Horizon 0.9B Institute of Foundation Models | 0.0% | — | — | — | |
| 123 | K2 Horizon 3.7B Institute of Foundation Models | 0.0% | — | — | — | |
| 124 | K2 Horizon MoVA 36B A4B Institute of Foundation Models | 0.0% | — | — | — | |
| 125 | Ling-3.0-flash-Fin InclusionAI | 0.0% | — | — | — | |
| 126 | Ling-3.0-flash-VL InclusionAI | 0.0% | — | — | — | |
| 127 | Ling 3.0 Tiny InclusionAI | 0.0% | — | — | — | |
| 128 |  Llama 4 Maverick Meta | 0.0% | — | — | — | |
| 129 | Llama 4 Scout Meta | 0.0% | — | — | — | |
| 130 |  LongCat 2.0 LongCat | 0.0% | — | — | — | |
| 131 |  Mercury 2.5 Inception | 0.0% | — | — | — | |
| 132 |  MiniCPM5-2B OpenBMB | 0.0% | — | — | — | |
| 133 |  Ministral 3 14B Mistral | 0.0% | — | — | — | |
| 134 | Ministral 3 3B Mistral | 0.0% | — | — | — | |
| 135 | Ministral 3 8B Mistral | 0.0% | — | — | — | |
| 136 | Mistral Medium 3.5 Mistral | 0.0% | $1.70 | 8m 1s | 67.3K | |
| 137 | Mistral Small 4 (Reasoning) Mistral | 0.0% | $0.062 | 3m 3s | 26.7K | |
| 138 | 0.0% | — | — | — | ||
| 139 | Nemotron 3.5 Super VL NVIDIA | 0.0% | $0.73 | 9m 36s | 149K | |
| 140 | 0.0% | — | — | — | ||
| 141 | 0.0% | — | — | 6.45K | ||
| 142 | 0.0% | — | — | — | ||
| 143 | 0.0% | — | — | — | ||
| 144 | Qwen3.6 35B A3B (Reasoning) Alibaba | 0.0% | — | — | — | |
| 145 | Qwen3.8 27B (Non-reasoning) Alibaba | 0.0% | $9.39 | 42m 25s | 104K | |
| 146 | Qwen3 Coder Next Alibaba | 0.0% | — | — | — | |
| 147 |  Solar Pro 4 Upstage | 0.0% | — | — | — |
