← ランキング一覧
🤖 AI Agents (Autonomous AI)
An AI's ability to autonomously execute multi-step actions to complete a task — beyond just answering questions. For example, given "book flights + hotel for a weekend trip to Da Nang, budget under 5 million" — the AI must search flights, compare prices, fill forms, and resolve errors on its own without step-by-step guidance. Measured via τ²-bench (dialogue + tool use) and Terminal-Bench v2 (multi-step terminal/computer tasks).
100/100 件のモデル
| # | アクセス | |||
|---|---|---|---|---|
| 1 | Anthropic | 99.3 | 試す | |
| 2 | OpenAI | 98.0 | 試す | |
| 3 | China Mobile | 97.1 | – | |
| 4 | Alibaba | 96.9 | 試す | |
| 5 | Anthropic | 96.5 | 試す | |
| 6 | SpaceXAI | 96.1 | – | |
| 7 | Google | 95.9 | 試す | |
| 8 | Z AI | 95.8 | 試す | |
| 9 | Z AI | 95.4 | 試す | |
| 10 | Z AI | 94.6 | 試す | |
| 11 | Z AI | 94.5 | 試す | |
| 12 | Alibaba | 94.3 | 試す | |
| 13 | Anthropic | 94.3 | 試す | |
| 14 | Alibaba | 93.9 | 試す | |
| 15 | Meta | 93.8 | 試す | |
| 16 | Google | 93.7 | 試す | |
| 17 | SpaceXAI | 93.6 | 試す | |
| 18 | Z AI | 92.6 | 試す | |
| 19 | Xiaomi | 92.5 | – | |
| 20 | Kimi | 92.5 | 試す | |
| 21 | Anthropic | 92.3 | 試す | |
| 22 | Z AI | 92.1 | 試す | |
| 23 | MiniMax | 92.0 | 試す | |
| 24 | Z AI | 91.5 | 試す | |
| 25 | OpenAI | 91.4 | 試す | |
| 26 | China Mobile | 91.3 | – | |
| 27 | Tencent | 91.2 | – | |
| 28 | OpenAI | 91.2 | 試す | |
| 29 | OpenAI | 91.1 | 試す | |
| 30 | SpaceXAI | 91.1 | – | |
| 31 | StepFun | 91.1 | 試す | |
| 32 | Alibaba | 91.0 | 試す | |
| 33 | Trillion Labs | 90.2 | – | |
| 34 | Alibaba | 90.2 | 試す | |
| 35 | Google | 89.8 | 試す | |
| 36 | Xiaomi | 89.2 | – | |
| 37 | SpaceXAI | 89.2 | 試す | |
| 38 | Anthropic | 89.1 | 試す | |
| 39 | InclusionAI | 88.7 | – | |
| 40 | SpaceXAI | 88.6 | – | |
| 41 | OpenAI | 88.5 | 試す | |
| 42 | Meta | 88.3 | 試す | |
| 43 | Anthropic | 88.2 | 試す | |
| 44 | Alibaba | 88.2 | 試す | |
| 45 | Kimi | 88.1 | 試す | |
| 46 | OpenAI | 88.0 | 試す | |
| 47 | Anthropic | 88.0 | 試す | |
| 48 | Alibaba | 87.5 | 試す | |
| 49 | DeepSeek | 87.1 | 試す | |
| 50 | Alibaba | 86.9 | 試す | |
| 51 | DeepSeek | 86.8 | 試す | |
| 52 | Xiaomi | 86.6 | – | |
| 53 | StepFun | 86.3 | 試す | |
| 54 | Google | 85.8 | 試す | |
| 55 | Meta | 85.7 | 試す | |
| 56 | Google | 85.6 | 試す | |
| 57 | Anthropic | 85.4 | 試す | |
| 58 | OpenAI | 84.5 | 試す | |
| 59 | KwaiKAT | 84.4 | 試す | |
| 60 | 84.3 | – | ||
| 61 | OpenAI | 83.9 | 試す | |
| 62 | Alibaba | 83.7 | 試す | |
| 63 | Motif Technologies | 83.6 | – | |
| 64 | Kimi | 83.4 | 試す | |
| 65 | Google | 83.3 | 試す | |
| 66 | Korea Telecom | 83.3 | – | |
| 67 | DeepSeek | 83.1 | 試す | |
| 68 | DeepSeek | 83.1 | 試す | |
| 69 | OpenBMB | 83.1 | – | |
| 70 | SpaceXAI | 82.7 | – | |
| 71 | Kimi | 82.7 | 試す | |
| 72 | MiniMax | 82.6 | 試す | |
| 73 | MiniMax | 82.5 | 試す | |
| 74 | Xiaomi | 82.4 | – | |
| 75 | KwaiKAT | 82.1 | – | |
| 76 | Z AI | 82.0 | 試す | |
| 77 | OpenAI | 81.9 | 試す | |
| 78 | OpenAI | 81.8 | 試す | |
| 79 | Alibaba | 81.7 | 試す | |
| 80 | Alibaba | 81.7 | 試す | |
| 81 | DeepSeek | 81.5 | 試す | |
| 82 | Institute of Foundation Models | 81.2 | – | |
| 83 | MiniMax | 80.9 | 試す | |
| 84 | Alibaba | 80.7 | 試す | |
| 85 | 80.4 | 試す | ||
| 86 | Alibaba | 80.3 | 試す | |
| 87 | Xiaomi | 80.2 | – | |
| 88 | Trillion Labs | 79.7 | – | |
| 89 | OpenAI | 79.7 | 試す | |
| 90 | Meta | 79.6 | 試す | |
| 91 | Apodex | 79.1 | – | |
| 92 | Nex AGI | 79.0 | – | |
| 93 | Xiaomi | 78.6 | 試す | |
| 94 | Multiverse Computing | 78.3 | – | |
| 95 | LongCat | 78.2 | – | |
| 96 | Google | 78.1 | 試す | |
| 97 | Amazon | 77.7 | 試す | |
| 98 | Anthropic | 77.6 | 試す | |
| 99 | Mistral | 75.7 | 試す | |
| 100 | Alibaba | 75.2 | 試す |