모델 순위
모델 326개 · 순위표 2개 · 데이터 출처 2곳
가장 똑똑한 모델
오픈 모델 1위
중국 모델 1위
오픈 모델 상위 3
Qwen3 235B A22B (Reasoning)Alibaba · 전체 6위62.3
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA · 전체 8위60.8
DeepSeek R1DeepSeek · 전체 10위60.2
이번 주 변동
Qwen3 235B A22B (Reasoning)지능 · 6위신규
Qwen3 32B (Reasoning)지능 · 11위신규
Qwen3 14B (Reasoning)지능 · 14위신규
Qwen3 30B A3B (Reasoning)지능 · 15위신규
Nova Premier지능 · 37위신규
| 순위 | 변동 | 모델 | 지능 | 가격 $/M | 속도 tok/s | 첫 토큰 |
|---|---|---|---|---|---|---|
| 1 | 신규 | Qwen3 235B A22B (Reasoning)오픈Alibaba | 62.3 | — | — | — |
| 2 | ▼ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA | 60.8 | — | — | — |
| 3 | ▼ 1 | DeepSeek R1오픈DeepSeek | 60.2 | — | — | — |
| 4 | 신규 | Qwen3 32B (Reasoning)오픈Alibaba | 59.2 | — | — | — |
| 5 | ▼ 2 | QwQ 32B오픈Alibaba | 58.1 | — | — | — |
| 6 | 신규 | Qwen3 14B (Reasoning)오픈Alibaba | 55.7 | — | — | — |
| 7 | 신규 | Qwen3 30B A3B (Reasoning)오픈Alibaba | 55.6 | — | — | — |
| 8 | ▼ 4 | DeepSeek V3 0324 (Mar' 25)오픈DeepSeek · 변형 1개 더 | 53.2 | — | — | — |
| 9 | ▼ 4 | DeepSeek R1 Distill Qwen 32B오픈DeepSeek | 51.9 | — | — | — |
| 10 | ▼ 4 | Llama 4 Maverick오픈Meta | 50.5 | — | — | — |
| 11 | ▼ 4 | DeepSeek R1 Distill Qwen 14B오픈DeepSeek | 49.0 | — | — | — |
| 12 | ▼ 4 | DeepSeek R1 Distill Llama 70B오픈DeepSeek | 48.2 | — | — | — |
| 13 | ▼ 4 | Reka Flash 3오픈Reka AI | 47.1 | — | — | — |
| 14 | ▼ 4 | Llama 4 Scout오픈Meta | 43.0 | — | — | — |
| 15 | ▼ 4 | QwQ 32B-Preview오픈Alibaba | 42.6 | — | — | — |
| 16 | ▼ 4 | Llama 3.3 Instruct 70B오픈Meta | 41.1 | — | — | — |
| 17 | ▼ 4 | Llama 3.1 Instruct 405B오픈Meta | 40.5 | — | — | — |
| 18 | ▼ 4 | Qwen2.5 Instruct 72B오픈Alibaba | 40.4 | — | — | — |
| 19 | ▼ 4 | MiniMax-Text-01오픈MiniMax | 40.2 | — | — | — |
| 20 | ▼ 4 | Phi-4오픈Microsoft Azure | 40.2 | — | — | — |
| 21 | ▼ 4 | Command A오픈Cohere | 40.0 | — | — | — |
| 22 | ▼ 4 | Llama 3.1 Tulu3 405B오픈Allen Institute for AI | 39.9 | — | — | — |
| 23 | ▼ 4 | Llama 3.3 Nemotron Super 49B v1오픈NVIDIA | 39.3 | — | — | — |
| 24 | ▼ 4 | Mistral Large 2 (Nov '24)오픈Mistral · 변형 1개 더 | 38.3 | — | — | — |
| 25 | ▼ 4 | Gemma 3 27B Instruct오픈Google | 37.6 | — | — | — |
| 26 | ▼ 4 | Pixtral Large오픈Mistral | 37.4 | — | — | — |
| 27 | ▼ 4 | Qwen2.5 Instruct 32B오픈Alibaba | 37.4 | — | — | — |
| 28 | ▼ 4 | Llama 3.1 Nemotron Instruct 70B오픈NVIDIA | 37.3 | — | — | — |
| 29 | ▼ 4 | Qwen2.5 Coder Instruct 32B오픈Alibaba | 36.3 | — | — | — |
| 30 | ▼ 4 | Llama 3.1 Instruct 70B오픈Meta | 35.4 | — | — | — |
| 31 | ▼ 4 | Mistral Small 3.1오픈Mistral | 35.3 | — | — | — |
| 32 | ▼ 4 | Mistral Small 3오픈Mistral | 35.3 | — | — | — |
| 33 | ▼ 4 | DeepSeek R1 Distill Llama 8B오픈DeepSeek | 34.0 | — | — | — |
| 34 | ▼ 4 | Gemma 3 12B Instruct오픈Google | 33.8 | — | — | — |
| 35 | ▼ 4 | Llama 3.2 Instruct 90B (Vision)오픈Meta | 33.4 | — | — | — |
| 36 | ▼ 4 | Qwen2 Instruct 72B오픈Alibaba | 32.6 | — | — | — |
| 37 | ▼ 4 | DeepHermes 3 - Mistral 24B Preview오픈Nous Research | 30.0 | — | — | — |
| 38 | ▼ 4 | Jamba 1.5 Large오픈AI21 Labs | 29.3 | — | — | — |
| 39 | ▼ 4 | Hermes 3 - Llama-3.1 70B오픈Nous Research | 29.1 | — | — | — |
| 40 | ▼ 4 | Jamba 1.6 Large오픈AI21 Labs | 28.8 | — | — | — |
| 41 | ▼ 4 | Llama 3 Instruct 70B오픈Meta | 27.5 | — | — | — |
| 42 | ▼ 4 | Mistral Small (Sep '24)오픈Mistral | 27.4 | — | — | — |
| 43 | ▼ 4 | Phi-4 Multimodal Instruct오픈Microsoft Azure | 26.9 | — | — | — |
| 44 | ▼ 4 | Qwen2.5 Coder Instruct 7B오픈Alibaba | 26.7 | — | — | — |
| 45 | ▼ 4 | Mixtral 8x22B Instruct오픈Mistral | 26.2 | — | — | — |
| 46 | ▼ 4 | Phi-4 Mini Instruct오픈Microsoft Azure | 26.0 | — | — | — |
| 47 | ▼ 4 | Phi-3 Medium Instruct 14B오픈Microsoft Azure | 24.5 | — | — | — |
| 48 | ▼ 4 | Gemma 3 4B Instruct오픈Google | 24.5 | — | — | — |
| 49 | ▼ 4 | Llama 3.1 Instruct 8B오픈Meta | 23.7 | — | — | — |
| 50 | ▼ 4 | Pixtral 12B (2409)오픈Mistral | 23.4 | — | — | — |
지능의 발전
가장 많이 오름 · Anthropic +57.2현재 최고 · Anthropic 64.6최고와 최저의 차이 18.1점기간 2025년 11월 – 2026년 11월
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi