← Todos os rankings
🧠 Reasoning
Reasoning capabilities & academic knowledge — GPQA Diamond, MMLU-Pro, HLE.
100/100 modelos
| # | Acesso | |||
|---|---|---|---|---|
| 1 | OpenAI | 99.4 | Testar agora | |
| 2 | Google | 98.4 | Testar agora | |
| 3 | SpaceXAI | 97.5 | – | |
| 4 | Meta | 97.2 | Testar agora | |
| 5 | Google | 97.2 | Testar agora | |
| 6 | Anthropic | 96.8 | Testar agora | |
| 7 | Alibaba | 96.2 | Testar agora | |
| 8 | OpenAI | 96.1 | Testar agora | |
| 9 | Anthropic | 96.0 | Testar agora | |
| 10 | Alibaba | 95.9 | Testar agora | |
| 11 | Kimi | 95.6 | Testar agora | |
| 12 | DeepSeek | 95.5 | Testar agora | |
| 13 | Alibaba | 95.3 | Testar agora | |
| 14 | SpaceXAI | 95.1 | Testar agora | |
| 15 | Google | 95.0 | Testar agora | |
| 16 | Z AI | 94.5 | Testar agora | |
| 17 | OpenAI | 94.5 | Testar agora | |
| 18 | Z AI | 94.2 | Testar agora | |
| 19 | DeepSeek | 94.2 | Testar agora | |
| 20 | MiniMax | 94.1 | Testar agora | |
| 21 | Anthropic | 94.0 | Testar agora | |
| 22 | OpenAI | 94.0 | Testar agora | |
| 23 | Alibaba | 93.3 | Testar agora | |
| 24 | Google | 93.3 | Testar agora | |
| 25 | DeepSeek | 93.3 | Testar agora | |
| 26 | Alibaba | 93.3 | Testar agora | |
| 27 | Google | 93.2 | Testar agora | |
| 28 | Anthropic | 93.2 | Testar agora | |
| 29 | OpenAI | 93.1 | Testar agora | |
| 30 | Meta | 93.0 | Testar agora | |
| 31 | Anthropic | 93.0 | Testar agora | |
| 32 | Thinking Machines | 92.0 | – | |
| 33 | Meta | 91.9 | Testar agora | |
| 34 | Anthropic | 91.7 | Testar agora | |
| 35 | Upstage | 91.7 | – | |
| 36 | Tencent | 91.7 | – | |
| 37 | Kimi | 91.5 | Testar agora | |
| 38 | OpenAI | 91.5 | Testar agora | |
| 39 | Alibaba | 91.3 | Testar agora | |
| 40 | SpaceXAI | 91.3 | – | |
| 41 | Kimi | 91.1 | Testar agora | |
| 42 | SpaceXAI | 91.1 | – | |
| 43 | Z AI | 91.1 | Testar agora | |
| 44 | DeepSeek | 91.0 | Testar agora | |
| 45 | SpaceXAI | 90.8 | – | |
| 46 | Nex AGI | 90.5 | – | |
| 47 | Institute of Foundation Models | 90.5 | – | |
| 48 | OpenAI | 90.4 | Testar agora | |
| 49 | DeepSeek | 89.9 | Testar agora | |
| 50 | Motif Technologies | 89.7 | – | |
| 51 | InclusionAI | 89.6 | – | |
| 52 | Apodex | 89.6 | – | |
| 53 | Thinking Machines | 89.4 | – | |
| 54 | Alibaba | 89.3 | Testar agora | |
| 55 | Meta | 88.6 | Testar agora | |
| 56 | Anthropic | 88.6 | Testar agora | |
| 57 | SK Telecom | 88.5 | – | |
| 58 | Upstage | 88.5 | – | |
| 59 | Alibaba | 88.5 | Testar agora | |
| 60 | Alibaba | 88.3 | Testar agora | |
| 61 | Google | 88.2 | Testar agora | |
| 62 | SpaceXAI | 88.2 | Testar agora | |
| 63 | InclusionAI | 88.2 | – | |
| 64 | OpenAI | 88.1 | Testar agora | |
| 65 | 88.1 | Testar agora | ||
| 66 | Google | 87.8 | Testar agora | |
| 67 | OpenAI | 87.8 | Testar agora | |
| 68 | OpenAI | 87.3 | Testar agora | |
| 69 | Tencent | 87.3 | – | |
| 70 | MiniMax | 87.2 | Testar agora | |
| 71 | Xiaomi | 87.2 | – | |
| 72 | Z AI | 87.0 | Testar agora | |
| 73 | Xiaomi | 86.8 | – | |
| 74 | Anthropic | 86.8 | Testar agora | |
| 75 | Kimi | 86.7 | Testar agora | |
| 76 | China Mobile | 86.6 | – | |
| 77 | InclusionAI | 86.6 | – | |
| 78 | OpenAI | 86.5 | Testar agora | |
| 79 | Meta | 86.3 | Testar agora | |
| 80 | Google | 86.2 | Testar agora | |
| 81 | Google | 85.9 | Testar agora | |
| 82 | LG AI Research | 85.8 | – | |
| 83 | KwaiKAT | 85.6 | – | |
| 84 | Xiaomi | 85.6 | – | |
| 85 | Institute of Foundation Models | 85.5 | – | |
| 86 | Xiaomi | 85.5 | – | |
| 87 | Alibaba | 85.2 | Testar agora | |
| 88 | Alibaba | 85.1 | Testar agora | |
| 89 | Alibaba | 84.9 | Testar agora | |
| 90 | DeepSeek | 84.8 | Testar agora | |
| 91 | Alibaba | 84.8 | Testar agora | |
| 92 | OpenAI | 84.6 | Testar agora | |
| 93 | Alibaba | 84.6 | Testar agora | |
| 94 | Z AI | 84.5 | Testar agora | |
| 95 | Anthropic | 84.2 | Testar agora | |
| 96 | Nanbeige | 84.1 | – | |
| 97 | Z AI | 84.0 | Testar agora | |
| 98 | MiniMax | 84.0 | Testar agora | |
| 99 | China Mobile | 84.0 | – | |
| 100 | Alibaba | 83.9 | Testar agora |
Como funciona a pontuação — AIM Index
● Capacidade 85%● Recência 15%
GPQA DiamondARC-AGIHLE
Fontes de dados (1)