HyperAI
Command Palette
Search for a command to run...
Terminal-Bench 2.1
Terminal-Bench 2.0 的验证刷新版：89 个精选任务，涵盖软件工程、系统管理、数据处理、模型训练和安全，并修复了环境与指令问题，使分数反映智能体能力而非环境缺陷。
- 模型
- 114 当前，243 总共
- 中位数
- 38.6%
- 范围
- 0.0%–89.9%
| 排名 | 比较 | 模型 | 评分 |
|---|---|---|---|
| 51 |  Solar Open2 250B Upstage | 44.2% | |
| 52 |  Gemma 4 31B (Reasoning) Google | 43.4% | |
| 53 |  Ring-2.6-1T InclusionAI | 43.1% | |
| 54 | 41.6% | ||
| 55 |  K-EXAONE 2.0 LG AI Research | 40.4% | |
| 56 |  A.X-K2 SK Telecom | 39.0% | |
| 57 | 39.0% | ||
| 58 |  Qwen3 Coder Next Alibaba | 38.2% | |
| 59 |  North Mini Code Cohere | 35.6% | |
| 60 | 34.8% | ||
| 61 |  G9v3-39A5B AI9Stars | 32.6% | |
| 62 | 29.6% | ||
| 63 | 29.2% | ||
| 64 | Qwen3.5 9B (Reasoning) Alibaba | 29.2% | |
| 65 |  K2 Horizon 3.7B Institute of Foundation Models | 28.1% | |
| 66 | Ling 3.0 Tiny InclusionAI | 27.7% | |
| 67 | Gemma 4 12B (Reasoning) Google | 27.3% | |
| 68 | 26.6% | ||
| 69 |  gpt-oss-120b (High) OpenAI | 26.2% | |
| 70 | Qwen3.5 4B (Reasoning) Alibaba | 25.8% | |
| 71 |  Nemotron 3.5 Lightning NVIDIA | 24.3% | |
| 72 | Command A+ Cohere | 22.8% | |
| 73 | EXAONE 4.5 33B (Reasoning) LG AI Research | 21.3% | |
| 74 | Qwen3.5 4B (Non-reasoning) Alibaba | 21.3% | |
| 75 | Qwen3.5 9B (Non-reasoning) Alibaba | 21.3% | |
| 76 |  Mistral Small 4 (Reasoning) Mistral | 21.0% | |
| 77 | 20.6% | ||
| 78 |  Trinity Large Thinking Arcee AI | 20.6% | |
| 79 | 19.5% | ||
| 80 | 18.4% | ||
| 81 |  HyperNova 60B 2605 (High, Based on gpt-oss-120b) Multiverse Computing | 18.4% | |
| 82 | 17.2% | ||
| 83 |  Nova 2.0 Lite (High) Amazon | 16.1% | |
| 84 | K2 Think V2 Institute of Foundation Models | 15.0% | |
| 85 | gpt-oss-120b (Low) OpenAI | 13.9% | |
| 86 | gpt-oss-20b (High) OpenAI | 13.9% | |
| 87 | 13.9% | ||
| 88 | DiffusionGemma 26B A4B Google | 12.4% | |
| 89 | Magistral Medium 1.2 Mistral | 12.4% | |
| 90 |  Celeris-1 Celeris | 11.2% | |
| 91 | Ministral 3 14B Mistral | 9.7% | |
| 92 |  MiniCPM5-2B OpenBMB | 8.6% | |
| 93 |  Llama 4 Maverick Meta | 7.9% | |
| 94 | 6.7% | ||
| 95 | 6.7% | ||
| 96 | 6.7% | ||
| 97 | G9v3-3B AI9Stars | 6.0% | |
| 98 | 4.9% | ||
| 99 |  LFM2.5-2.6B Liquid AI | 4.5% | |
| 100 | Magistral Small 1.2 Mistral | 4.5% |
