모델 순위
모델 526개 · 순위표 3개 · 데이터 출처 2곳
가장 똑똑한 모델
오픈 모델 1위
가성비 1위
중국 모델 1위
오픈 모델 상위 3
gpt-oss-120BOpenAI · 전체 9위57.9
Qwen3 235B A22B 2507 (Reasoning)Alibaba · 전체 10위57.5
DeepSeek V3.1 (Reasoning)DeepSeek · 전체 15위54.0
이번 주 변동
Grok Code Fast 1지능 · 22위신규
Qwen3 Max (Preview)지능 · 23위신규
Hermes 4 - Llama-3.1 405B (Reasoning)지능 · 40위신규
Hermes 4 - Llama-3.1 70B (Reasoning)지능 · 45위신규
Kimi K2 0905지능 · 19위12계단 상승
| 순위 | 변동 | 모델 | 지능 | 가격 $/M | 속도 tok/s | 첫 토큰 |
|---|---|---|---|---|---|---|
| 1 | — | GPT-5 (high)클로즈드OpenAI | 66.7 | $3.4 | — | — |
| 2 | — | GPT-5 (medium)클로즈드OpenAI | 66.3 | $3.4 | — | — |
| 3 | — | Grok 4클로즈드xAI | 65.3 | $6.0 | — | — |
| 4 | — | o3-pro클로즈드OpenAI | 65.3 | $35 | — | — |
| 5 | — | o3클로즈드OpenAI | 65.2 | $3.5 | — | — |
| 6 | — | GPT-5 mini (high)클로즈드OpenAI | 62.3 | $0.69 | — | — |
| 7 | ▲ 3 | GPT-5 (low)클로즈드OpenAI | 61.7 | $3.4 | — | — |
| 8 | ▲ 1 | GPT-5 mini (medium)클로즈드OpenAI | 60.8 | $0.69 | — | — |
| 9 | ▼ 1 | Gemini 2.5 Pro클로즈드Google | 59.6 | $3.4 | — | — |
| 10 | ▲ 1 | Claude 4.1 Opus (Extended Thinking)클로즈드Anthropic | 59.3 | $30 | — | — |
| 11 | ▼ 4 | o4-mini (high)클로즈드OpenAI | 59.0 | $1.9 | — | — |
| 12 | ▲ 3 | Grok 3 mini Reasoning (high)클로즈드xAI | 57.1 | $0.35 | — | — |
| 13 | — | Claude 4 Sonnet (Extended Thinking)클로즈드Anthropic | 56.5 | $6.0 | — | — |
| 14 | ▲ 4 | Claude 4 Opus (Extended Thinking)클로즈드Anthropic | 54.2 | $30 | — | — |
| 15 | ▼ 3 | Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google | 54.1 | $3.4 | — | — |
| 16 | — | Gemini 2.5 Pro Preview (May' 25)클로즈드Google | 53.2 | $3.4 | — | — |
| 17 | ▼ 3 | Gemini 2.5 Flash (Reasoning)클로즈드Google | 51.2 | $0.85 | — | — |
| 18 | ▼ 1 | o3-mini (high)클로즈드OpenAI | 50.8 | $1.9 | — | — |
| 19 | 신규 | Grok Code Fast 1클로즈드xAI | 48.7 | $0.53 | — | — |
| 20 | 신규 | Qwen3 Max (Preview)클로즈드Alibaba | 48.6 | $2.4 | — | — |
| 21 | ▼ 2 | GPT-5 nano (high)클로즈드OpenAI | 48.5 | $0.14 | — | — |
| 22 | ▼ 1 | o3-mini클로즈드OpenAI | 48.1 | $1.9 | — | — |
| 23 | ▲ 11 | o1-pro클로즈드OpenAI | 48.0 | $263 | — | — |
| 24 | ▼ 4 | GPT-5 nano (medium)클로즈드OpenAI | 47.7 | $0.14 | — | — |
| 25 | ▼ 3 | o1클로즈드OpenAI | 47.2 | $26 | — | — |
| 26 | ▼ 3 | Sonar Reasoning Pro클로즈드Perplexity | 46.3 | $0.000 | — | — |
| 27 | ▼ 3 | Gemini 2.5 Flash Preview (Reasoning)클로즈드Google | 45.8 | $0.000 | — | — |
| 28 | ▼ 3 | o1-preview클로즈드OpenAI | 44.9 | $29 | — | — |
| 29 | ▼ 3 | Claude 4.1 Opus클로즈드Anthropic | 44.6 | $30 | — | — |
| 30 | ▲ 3 | Claude 4 Sonnet클로즈드Anthropic | 44.4 | $6.0 | — | — |
| 31 | ▲ 6 | GPT-5 (minimal)클로즈드OpenAI | 43.5 | $3.4 | — | — |
| 32 | ▼ 2 | GPT-4.1클로즈드OpenAI | 43.4 | $3.5 | — | — |
| 33 | ▼ 4 | Claude 3.7 Sonnet (Extended Thinking)클로즈드Anthropic | 42.7 | $6.0 | — | — |
| 34 | ▲ 2 | GPT-4.1 mini클로즈드OpenAI | 42.5 | $0.70 | — | — |
| 35 | ▼ 4 | Claude 4 Opus클로즈드Anthropic | 42.3 | $30 | — | — |
| 36 | ▼ 4 | GPT-5 mini (minimal)클로즈드OpenAI | 41.6 | $0.69 | — | — |
| 37 | ▼ 3 | Grok 3 Reasoning Beta클로즈드xAI | 41.4 | $0.000 | — | — |
| 38 | ▼ 11 | Gemini 2.5 Flash클로즈드Google | 40.4 | $0.85 | — | — |
| 39 | ▼ 11 | Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google | 40.1 | $0.18 | — | — |
| 40 | ▼ 1 | o1-mini클로즈드OpenAI | 39.2 | $1.9 | — | — |
| 41 | ▼ 1 | GPT-4.5 (Preview)클로즈드OpenAI | 38.4 | $0.000 | — | — |
| 42 | ▼ 4 | Solar Pro 2 (Reasoning)클로즈드Upstage | 37.7 | $0.50 | — | — |
| 43 | ▼ 2 | Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google | 37.7 | $0.000 | — | — |
| 44 | ▼ 2 | Solar Pro 2 (Preview) (Reasoning)클로즈드Upstage | 36.1 | $0.000 | — | — |
| 45 | ▼ 2 | Grok 3클로즈드xAI | 36.0 | $6.0 | — | — |
| 46 | ▼ 2 | GPT-4o (March 2025, chatgpt-4o-latest)클로즈드OpenAI | 35.6 | $7.5 | — | — |
| 47 | ▲ 1 | Mistral Medium 3.1클로즈드Mistral | 35.4 | $0.80 | — | — |
| 48 | ▼ 3 | Mistral Medium 3클로즈드Mistral | 34.7 | $0.80 | — | — |
| 49 | ▼ 3 | Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google | 34.6 | $0.000 | — | — |
| 50 | ▼ 3 | Sonar Reasoning클로즈드Perplexity | 34.2 | $2.0 | — | — |
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