모델 순위
모델 521개 · 순위표 3개 · 데이터 출처 2곳
가장 똑똑한 모델
오픈 모델 1위
가성비 1위
중국 모델 1위
오픈 모델 상위 3
Qwen3 235B A22B 2507 (Reasoning)Alibaba · 전체 8위63.6
gpt-oss-120BOpenAI · 전체 9위61.3
DeepSeek V3.1 (Reasoning)DeepSeek · 전체 11위59.7
이번 주 변동
Exaone 4.0 1.2B (Reasoning)지능 · 81위신규
Qwen3 4B 2507 (Reasoning)지능 · 26위59계단 상승
Qwen3 0.6B (Reasoning)지능 · 148위10계단 상승
| 순위 | 변동 | 모델 | 지능 | 가격 $/M | 속도 tok/s | 첫 토큰 |
|---|---|---|---|---|---|---|
| 1 | — | GPT-5 (high)클로즈드OpenAI · 변형 3개 더 | 69.0 | $3.4 | — | — |
| 2 | — | Grok 4클로즈드xAI | 67.5 | $6.0 | — | — |
| 3 | — | o3-pro클로즈드OpenAI | 67.5 | $35 | — | — |
| 4 | — | o3클로즈드OpenAI | 67.1 | $3.5 | — | — |
| 5 | — | GPT-5 mini (high)클로즈드OpenAI · 변형 2개 더 | 65.4 | $0.69 | — | — |
| 6 | — | o4-mini (high)클로즈드OpenAI | 65.1 | $1.9 | — | — |
| 7 | — | Gemini 2.5 Pro클로즈드Google | 64.6 | $3.4 | — | — |
| 8 | — | Claude 4.1 Opus (Extended Thinking)클로즈드Anthropic · 변형 1개 더 | 61.0 | $30 | — | — |
| 9 | — | Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google · 변형 1개 더 | 59.0 | $3.4 | — | — |
| 10 | — | Claude 4 Sonnet (Extended Thinking)클로즈드Anthropic · 변형 1개 더 | 58.8 | $6.0 | — | — |
| 11 | — | Gemini 2.5 Flash (Reasoning)클로즈드Google · 변형 1개 더 | 58.4 | $0.85 | — | — |
| 12 | — | Grok 3 mini Reasoning (high)클로즈드xAI | 58.0 | $0.35 | — | — |
| 13 | — | o3-mini (high)클로즈드OpenAI · 변형 1개 더 | 55.5 | $1.9 | — | — |
| 14 | — | Claude 4 Opus (Extended Thinking)클로즈드Anthropic · 변형 1개 더 | 55.3 | $30 | — | — |
| 15 | — | GPT-5 nano (high)클로즈드OpenAI · 변형 2개 더 | 54.7 | $0.14 | — | — |
| 16 | — | o1클로즈드OpenAI · 변형 1개 더 | 51.7 | $26 | — | — |
| 17 | — | Sonar Reasoning Pro클로즈드Perplexity | 50.7 | $0.000 | — | — |
| 18 | — | Gemini 2.5 Flash Preview (Reasoning)클로즈드Google · 변형 1개 더 | 50.2 | $0.99 | — | — |
| 19 | — | Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google · 변형 1개 더 | 47.3 | $0.18 | — | — |
| 20 | — | Claude 3.7 Sonnet (Extended Thinking)클로즈드Anthropic · 변형 1개 더 | 47.0 | $6.0 | — | — |
| 21 | — | GPT-4.1클로즈드OpenAI | 46.8 | $3.5 | — | — |
| 22 | — | Grok 3 Reasoning Beta클로즈드xAI | 45.6 | $0.000 | — | — |
| 22 | — | o1-pro클로즈드OpenAI | 45.6 | $263 | — | — |
| 24 | — | GPT-4.1 mini클로즈드OpenAI | 45.6 | $0.70 | — | — |
| 25 | — | Solar Pro 2 (Reasoning)클로즈드Upstage · 변형 3개 더 | 43.3 | $0.50 | — | — |
| 26 | — | o1-mini클로즈드OpenAI | 43.3 | $1.9 | — | — |
| 27 | — | GPT-4.5 (Preview)클로즈드OpenAI | 42.4 | $0.000 | — | — |
| 28 | — | Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google · 변형 1개 더 | 41.7 | $0.000 | — | — |
| 29 | — | Grok 3클로즈드xAI | 39.9 | $6.0 | — | — |
| 30 | — | GPT-4o (March 2025, chatgpt-4o-latest)클로즈드OpenAI · 변형 4개 더 | 39.5 | $7.5 | — | — |
| 31 | — | Mistral Medium 3클로즈드Mistral | 38.6 | $0.80 | — | — |
| 32 | — | Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google | 38.4 | $0.000 | — | — |
| 33 | — | Sonar Reasoning클로즈드Perplexity | 38.0 | $2.0 | — | — |
| 34 | — | Mistral Medium 3.1클로즈드Mistral | 38.0 | $0.80 | — | — |
| 35 | — | Gemini 2.0 Flash (Feb '25)클로즈드Google · 변형 1개 더 | 37.8 | $0.18 | — | — |
| 36 | — | Magistral Medium클로즈드Mistral | 37.6 | $2.8 | — | — |
| 37 | — | Nova Premier클로즈드Amazon | 34.8 | $5.0 | — | — |
| 38 | — | Qwen2.5 Max클로즈드Alibaba | 34.3 | $2.8 | — | — |
| 39 | — | Gemini 1.5 Pro (Sep '24)클로즈드Google · 변형 1개 더 | 33.6 | $0.000 | — | — |
| 40 | — | Claude 3.5 Sonnet (Oct '24)클로즈드Anthropic · 변형 1개 더 | 33.5 | $6.0 | — | — |
| 41 | — | Sonar클로즈드Perplexity | 32.4 | $1.0 | — | — |
| 42 | — | Sonar Pro클로즈드Perplexity | 31.7 | $6.0 | — | — |
| 43 | — | GPT-4.1 nano클로즈드OpenAI | 31.6 | $0.18 | — | — |
| 44 | — | Devstral Medium클로즈드Mistral | 31.3 | $0.80 | — | — |
| 45 | — | Gemini 2.0 Flash-Lite (Feb '25)클로즈드Google · 변형 1개 더 | 30.3 | $0.13 | — | — |
| 46 | — | Nova Pro클로즈드Amazon | 28.8 | $1.4 | — | — |
| 47 | ▲ 1 | Gemini 1.5 Flash (Sep '24)클로즈드Google · 변형 1개 더 | 27.7 | $0.000 | — | — |
| 48 | ▲ 1 | GPT-4 Turbo클로즈드OpenAI | 27.5 | $15 | — | — |
| 49 | ▲ 1 | Grok Beta클로즈드xAI | 26.3 | $0.000 | — | — |
| 50 | ▲ 1 | GPT-4클로즈드OpenAI | 24.6 | $38 | — | — |
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