AI Agents 프런티어 모델·에이전트 비교
이 페이지의 모든 수치는
Artificial
Analysis 원본 데이터의 미러 입니다
(핵심 지표 발췌 · 매일 UTC 00시 갱신). 모델명이 링크(📄)면 우리 논문 DB의
테크 리포트로 이동하고, "리더보드에서 논문 결과와 비교"는 논문 SOTA와 상용
모델이 한 표에 서는 병합 보드로 연결됩니다.
지표 필터 없음
Intelligence Index Coding Index Humanity's Last Exam (%) Price (USD/1M)
이상
미만
가성비 프런티어
지표 ↑ · 가격 ↓
선택한 지표 × 1M 토큰당 가격(혼합 3:1, 로그 축).
선은 파레토 프런티어 — 그 가격대에서 가장 좋은 모델입니다. 아래 칩으로
Y축 지표를 전환하고, 점을 누르면 관련 논문/테크 리포트로 이동합니다
(링크가 있는 모델만).
Intelligence Index
Coding Index
Humanity's Last Exam
Intelligence Index ↑
20
40
$0.1
$1
$10
$100
1M 토큰당 가격
(USD · 로그 축) →
Llama 3.1 Instruct 8B (Meta) — Intelligence Index 6.9, $0.028/1M tokens (클릭: 관련 논문)
Gemma 4 E4B (Reasoning) (Google) — Intelligence Index 8.9, $0.04/1M tokens (클릭: 관련 논문)
Gemma 4 E4B (Non-reasoning) (Google) — Intelligence Index 7.5, $0.04/1M tokens
Sarvam 30B (High) (Sarvam) — Intelligence Index 6.6, $0.047/1M tokens
Granite 4.2 3B (IBM) — Intelligence Index 9.1, $0.052/1M tokens
Mistral Small 3 (Mistral) — Intelligence Index 6.7, $0.058/1M tokens
Qwen3.5 4B (Reasoning) (Alibaba) — Intelligence Index 13.1, $0.06/1M tokens (클릭: 관련 논문)
Qwen3.5 4B (Non-reasoning) (Alibaba) — Intelligence Index 10.8, $0.06/1M tokens
Nova Micro (Amazon) — Intelligence Index 5.9, $0.061/1M tokens
NVIDIA Nemotron Nano 9B V2 (Reasoning) (NVIDIA) — Intelligence Index 7.4, $0.07/1M tokens
Llama 3 Instruct 8B (Meta) — Intelligence Index 4.8, $0.07/1M tokens
Sarvam 105B (High) (Sarvam) — Intelligence Index 8.8, $0.074/1M tokens
Granite 3.3 8B (Non-reasoning) (IBM) — Intelligence Index 4.9, $0.085/1M tokens
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) (NVIDIA) — Intelligence Index 6.8, $0.086/1M tokens
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA) — Intelligence Index 8.9, $0.088/1M tokens
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) (NVIDIA) — Intelligence Index 6.8, $0.088/1M tokens
Qwen2.5 Turbo (Alibaba) — Intelligence Index 6.4, $0.088/1M tokens
Nemotron 3.5 Lightning (NVIDIA) — Intelligence Index 12.9, $0.095/1M tokens (클릭: 관련 논문)
gpt-oss-20b (High) (OpenAI) — Intelligence Index 9.0, $0.098/1M tokens
Hy3-preview (Reasoning) (Tencent) — Intelligence Index 22.7, $0.1/1M tokens
Hy3-preview (Non-reasoning) (Tencent) — Intelligence Index 17.0, $0.1/1M tokens
Llama 2 Chat 7B (Meta) — Intelligence Index 5.7, $0.1/1M tokens
Ministral 3 3B (Mistral) — Intelligence Index 4.8, $0.1/1M tokens
Nova Lite (Amazon) — Intelligence Index 6.7, $0.105/1M tokens
gpt-oss-20b (Low) (OpenAI) — Intelligence Index 10.0, $0.106/1M tokens
Mistral Small 3.2 (Mistral) — Intelligence Index 8.2, $0.106/1M tokens
Granite 4.2 8B (IBM) — Intelligence Index 11.1, $0.107/1M tokens
Granite 4.0 H Small (IBM) — Intelligence Index 6.0, $0.107/1M tokens
Ling-3.0-flash-VL (InclusionAI) — Intelligence Index 24.6, $0.111/1M tokens
Ling-3.0-flash-Fin (InclusionAI) — Intelligence Index 22.6, $0.111/1M tokens
Ling 3.0 Flash (InclusionAI) — Intelligence Index 20.1, $0.111/1M tokens
DeepSeek V4 Flash 0420 (Non-reasoning) (DeepSeek) — Intelligence Index 18.9, $0.117/1M tokens
Mistral Small 3.1 (Mistral) — Intelligence Index 7.1, $0.125/1M tokens
Olmo 3 7B Instruct (Allen Institute for AI) — Intelligence Index 5.2, $0.125/1M tokens
Apertus 8B Instruct (Swiss AI Initiative) — Intelligence Index 4.8, $0.125/1M tokens
GPT-5 nano (High) (OpenAI) — Intelligence Index 13.0, $0.138/1M tokens
GPT-5 nano (Medium) (OpenAI) — Intelligence Index 12.5, $0.138/1M tokens
GPT-5 nano (Minimal) (OpenAI) — Intelligence Index 7.1, $0.138/1M tokens
MiMo-V2-Flash (Reasoning) (Xiaomi) — Intelligence Index 20.8, $0.15/1M tokens
Step 3.5 Flash 2603 (StepFun) — Intelligence Index 17.0, $0.15/1M tokens
Step 3.5 Flash (StepFun) — Intelligence Index 16.6, $0.15/1M tokens
Gemma 4 12B (Reasoning) (Google) — Intelligence Index 14.2, $0.15/1M tokens
Gemma 4 12B (Non-reasoning) (Google) — Intelligence Index 9.4, $0.15/1M tokens
Solar Mini (Upstage) — Intelligence Index 6.4, $0.15/1M tokens
Ministral 3 8B (Mistral) — Intelligence Index 5.5, $0.15/1M tokens
Qwen3.5 9B (Reasoning) (Alibaba) — Intelligence Index 11.2, $0.151/1M tokens
GLM-4.7-Flash (Reasoning) (Z AI) — Intelligence Index 14.9, $0.153/1M tokens
GLM-4.7-Flash (Non-reasoning) (Z AI) — Intelligence Index 10.6, $0.153/1M tokens
Mistral 7B Instruct (Mistral) — Intelligence Index 5.0, $0.162/1M tokens
DeepSeek V4 Flash 0420 (High) (DeepSeek) — Intelligence Index 24.4, $0.168/1M tokens
DeepSeek V4 Flash 0420 (Max) (DeepSeek) — Intelligence Index 24.2, $0.168/1M tokens
Gemma 4 26B A4B (Reasoning) (Google) — Intelligence Index 16.7, $0.168/1M tokens
MiMo-V2.6-Flash (Xiaomi) — Intelligence Index 37.9, $0.175/1M tokens (클릭: 관련 논문)
MiMo-V2.5 (Xiaomi) — Intelligence Index 25.2, $0.175/1M tokens
Solar Mini 4 (Upstage) — Intelligence Index 24.1, $0.175/1M tokens
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) (Google) — Intelligence Index 10.4, $0.175/1M tokens
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) (Google) — Intelligence Index 9.3, $0.175/1M tokens
Gemini 2.5 Flash-Lite (Reasoning) (Google) — Intelligence Index 8.5, $0.175/1M tokens
GPT-4.1 nano (OpenAI) — Intelligence Index 7.8, $0.175/1M tokens
Gemini 2.5 Flash-Lite (Non-reasoning) (Google) — Intelligence Index 6.7, $0.175/1M tokens
Qwen3.5 9B (Non-reasoning) (Alibaba) — Intelligence Index 13.3, $0.19/1M tokens
Gemma 4 26B A4B (Non-reasoning) (Google) — Intelligence Index 13.1, $0.198/1M tokens
Claude Haiku 5.5 (Max) (Anthropic) — Intelligence Index 43.4, $0.2/1M tokens
Claude Haiku 5.5 (Xhigh) (Anthropic) — Intelligence Index 41.2, $0.2/1M tokens
GPT-6 Luna (Max) (OpenAI) — Intelligence Index 38.1, $0.2/1M tokens
Claude Haiku 5.5 (High) (Anthropic) — Intelligence Index 37.8, $0.2/1M tokens
GPT-6 Luna (Xhigh) (OpenAI) — Intelligence Index 34.6, $0.2/1M tokens
Claude Haiku 5.5 (Medium) (Anthropic) — Intelligence Index 34.5, $0.2/1M tokens
GPT-6 Luna (High) (OpenAI) — Intelligence Index 32.9, $0.2/1M tokens
GPT-6 Luna (Medium) (OpenAI) — Intelligence Index 29.9, $0.2/1M tokens
Claude Haiku 5.5 (Low) (Anthropic) — Intelligence Index 29.4, $0.2/1M tokens
GPT-6 Luna (Low) (OpenAI) — Intelligence Index 21.5, $0.2/1M tokens
GPT-6 Luna (Non-reasoning) (OpenAI) — Intelligence Index 18.5, $0.2/1M tokens
Ministral 3 14B (Mistral) — Intelligence Index 6.0, $0.2/1M tokens
Phi-4 (Microsoft) — Intelligence Index 5.9, $0.219/1M tokens
Gemma 4 31B (Non-reasoning) (Google) — Intelligence Index 13.9, $0.224/1M tokens
Qwen3.8-Flash-Next (Alibaba) — Intelligence Index 39.8, $0.23/1M tokens (클릭: 관련 논문)
GLM 5.3 Flash (Z AI) — Intelligence Index 41.8, $0.237/1M tokens
Hy3 (Tencent) — Intelligence Index 25.3, $0.241/1M tokens
Ling-flash-2.0 (InclusionAI) — Intelligence Index 7.8, $0.247/1M tokens
Ring-flash-2.0 (InclusionAI) — Intelligence Index 7.2, $0.247/1M tokens
gpt-oss-120b (Low) (OpenAI) — Intelligence Index 10.2, $0.249/1M tokens
Jamba 1.5 Mini (AI21 Labs) — Intelligence Index 5.2, $0.25/1M tokens
gpt-oss-120b (High) (OpenAI) — Intelligence Index 11.6, $0.261/1M tokens
Mistral Small 4 (Reasoning) (Mistral) — Intelligence Index 11.3, $0.262/1M tokens
Mistral Small 4 (Non-reasoning) (Mistral) — Intelligence Index 9.0, $0.262/1M tokens
Solar Pro 3 (Upstage) — Intelligence Index 7.8, $0.262/1M tokens
GPT-4o mini (OpenAI) — Intelligence Index 6.7, $0.262/1M tokens
Grok 4 Fast (Reasoning) (SpaceXAI) — Intelligence Index 17.9, $0.275/1M tokens
Qwen3.5 Omni Flash (Alibaba) — Intelligence Index 12.5, $0.275/1M tokens
Grok 4 Fast (Non-reasoning) (SpaceXAI) — Intelligence Index 11.1, $0.275/1M tokens
Qwen3 VL 32B (Reasoning) (Alibaba) — Intelligence Index 11.9, $0.28/1M tokens
Qwen3 32B (Reasoning) (Alibaba) — Intelligence Index 8.6, $0.28/1M tokens
Qwen3 VL 32B Instruct (Alibaba) — Intelligence Index 8.4, $0.28/1M tokens
Qwen3 32B (Non-reasoning) (Alibaba) — Intelligence Index 7.3, $0.28/1M tokens
Granite 4.2 30B (IBM) — Intelligence Index 14.8, $0.282/1M tokens
Seed-OSS-36B-Instruct (ByteDance Seed) — Intelligence Index 12.1, $0.3/1M tokens
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) (NVIDIA) — Intelligence Index 5.8, $0.3/1M tokens
Qwen3 VL 8B Instruct (Alibaba) — Intelligence Index 7.3, $0.31/1M tokens
Qwen3 8B (Non-reasoning) (Alibaba) — Intelligence Index 6.0, $0.31/1M tokens
Llama 4 Scout (Meta) — Intelligence Index 8.1, $0.313/1M tokens
DeepSeek V3.2 (Reasoning) (DeepSeek) — Intelligence Index 21.5, $0.315/1M tokens
DeepSeek V3.2 Exp (Reasoning) (DeepSeek) — Intelligence Index 16.6, $0.315/1M tokens
DeepSeek V3.2 (Non-reasoning) (DeepSeek) — Intelligence Index 16.0, $0.315/1M tokens
DeepSeek V3.2 Exp (Non-reasoning) (DeepSeek) — Intelligence Index 13.9, $0.315/1M tokens
Celeris-1 (Celeris) — Intelligence Index 6.3, $0.325/1M tokens
Llama 3.2 Instruct 11B (Vision) (Meta) — Intelligence Index 5.4, $0.345/1M tokens
Grok 3 mini Reasoning (High) (SpaceXAI) — Intelligence Index 14.6, $0.35/1M tokens
Qwen3 VL 30B A3B Instruct (Alibaba) — Intelligence Index 7.9, $0.35/1M tokens
Qwen3 30B A3B 2507 Instruct (Alibaba) — Intelligence Index 7.5, $0.35/1M tokens
Qwen3 30B A3B (Non-reasoning) (Alibaba) — Intelligence Index 6.6, $0.35/1M tokens
Reka Flash (Sep '24) (Reka AI) — Intelligence Index 6.4, $0.35/1M tokens
Reka Flash 3 (Reka AI) — Intelligence Index 5.6, $0.35/1M tokens
GLM-4.5-Air (Z AI) — Intelligence Index 11.1, $0.372/1M tokens
Mercury 2 (Inception) — Intelligence Index 13.8, $0.375/1M tokens
Mercury 2.5 (Inception) — Intelligence Index 12.3, $0.375/1M tokens
Trinity Large Thinking (Arcee AI) — Intelligence Index 10.8, $0.388/1M tokens
Qwen3 235B A22B 2507 Instruct (Alibaba) — Intelligence Index 12.0, $0.403/1M tokens
Llama 4 Maverick (Meta) — Intelligence Index 10.0, $0.405/1M tokens
DeepSeek V3 0324 (DeepSeek) — Intelligence Index 9.7, $0.405/1M tokens
Qwen3 Next 80B A3B (Reasoning) (Alibaba) — Intelligence Index 11.2, $0.412/1M tokens
Qwen3 Next 80B A3B Instruct (Alibaba) — Intelligence Index 9.6, $0.412/1M tokens
Qwen3 Omni 30B A3B (Reasoning) (Alibaba) — Intelligence Index 7.8, $0.43/1M tokens
Qwen3 Omni 30B A3B Instruct (Alibaba) — Intelligence Index 6.0, $0.43/1M tokens
Step 3.7 Flash (StepFun) — Intelligence Index 19.5, $0.438/1M tokens
Ling 3.1 Flash (InclusionAI) — Intelligence Index 41.1, $0.45/1M tokens
GPT-5.6 Luna (Max) (OpenAI) — Intelligence Index 37.3, $0.45/1M tokens
GPT-5.6 Luna (Xhigh) (OpenAI) — Intelligence Index 34.6, $0.45/1M tokens
GPT-5.6 Luna (High) (OpenAI) — Intelligence Index 32.1, $0.45/1M tokens
GPT-5.6 Luna (Medium) (OpenAI) — Intelligence Index 25.0, $0.45/1M tokens
GPT-5.6 Luna (Low) (OpenAI) — Intelligence Index 21.0, $0.45/1M tokens
GPT-5.6 Luna (Non-reasoning) (OpenAI) — Intelligence Index 15.5, $0.45/1M tokens
Nemotron 3 Super 120B A12B (Reasoning) (NVIDIA) — Intelligence Index 12.8, $0.45/1M tokens
GLM-4.6V (Reasoning) (Z AI) — Intelligence Index 11.2, $0.45/1M tokens
Nemotron 3 Nano Omni 30B A3B Reasoning (NVIDIA) — Intelligence Index 10.3, $0.45/1M tokens
GLM-4.6V (Non-reasoning) (Z AI) — Intelligence Index 8.4, $0.45/1M tokens
DeepSeek V3.1 Terminus (Non-reasoning) (DeepSeek) — Intelligence Index 13.9, $0.453/1M tokens
GPT-5.4 nano (Xhigh) (OpenAI) — Intelligence Index 20.7, $0.463/1M tokens
GPT-5.4 nano (Medium) (OpenAI) — Intelligence Index 20.0, $0.463/1M tokens
GPT-5.4 nano (Non-reasoning) (OpenAI) — Intelligence Index 11.7, $0.463/1M tokens
DeepSeek V3 (Dec '24) (DeepSeek) — Intelligence Index 8.5, $0.463/1M tokens
Qwen2.5 Instruct 72B (Alibaba) — Intelligence Index 7.7, $0.48/1M tokens
ERNIE 4.5 300B A47B (Baidu) — Intelligence Index 7.5, $0.485/1M tokens
Claude 3 Haiku (Anthropic) — Intelligence Index 5.6, $0.5/1M tokens
Mixtral 8x7B Instruct (Mistral) — Intelligence Index 5.1, $0.512/1M tokens
DeepSeek V4.1 Flash (Max) (DeepSeek) — Intelligence Index 39.5, $0.525/1M tokens
MiniMax-M3 (MiniMax) — Intelligence Index 29.2, $0.525/1M tokens
Solar Pro 4 (Upstage) — Intelligence Index 28.2, $0.525/1M tokens
Inkling Small (Thinking Machines) — Intelligence Index 25.7, $0.525/1M tokens
DeepSeek V4.1 Flash (Non-reasoning) (DeepSeek) — Intelligence Index 24.7, $0.525/1M tokens
MiniMax-M2.5 (MiniMax) — Intelligence Index 22.8, $0.525/1M tokens
MiniMax-M2.7 (MiniMax) — Intelligence Index 22.8, $0.525/1M tokens
KAT Coder Pro V2 (KwaiKAT) — Intelligence Index 21.7, $0.525/1M tokens
MiniMax-M2.1 (MiniMax) — Intelligence Index 20.9, $0.525/1M tokens
LongCat 2.0 (LongCat) — Intelligence Index 19.1, $0.525/1M tokens
MiniMax-M2 (MiniMax) — Intelligence Index 18.6, $0.525/1M tokens
MiMo-V2.6-Pro (Xiaomi) — Intelligence Index 46.3, $0.544/1M tokens (클릭: 관련 논문)
DeepSeek V4 Pro 0424 (Max) (DeepSeek) — Intelligence Index 30.4, $0.544/1M tokens
DeepSeek V4 Pro 0424 (High) (DeepSeek) — Intelligence Index 30.1, $0.544/1M tokens
MiMo-V2.5-Pro (Reasoning) (Xiaomi) — Intelligence Index 26.0, $0.544/1M tokens
DeepSeek V4 Pro 0424 (Non-reasoning) (DeepSeek) — Intelligence Index 20.8, $0.544/1M tokens
MiMo-V2.5-Pro (Non-reasoning) (Xiaomi) — Intelligence Index 18.3, $0.544/1M tokens
Llama 3.1 Instruct 70B (Meta) — Intelligence Index 6.6, $0.56/1M tokens
Gemini 3.1 Flash-Lite (Google) — Intelligence Index 15.6, $0.563/1M tokens
Qwen3 Coder Next (Alibaba) — Intelligence Index 9.2, $0.563/1M tokens
Muse Glimmer (High) (Meta) — Intelligence Index 17.5, $0.581/1M tokens
Qwen3 14B (Non-reasoning) (Alibaba) — Intelligence Index 6.7, $0.612/1M tokens
DeepSeek V4 Flash Vision (Max) (DeepSeek) — Intelligence Index 34.8, $0.66/1M tokens
DeepSeek V4 Flash 0731 (Max) (DeepSeek) — Intelligence Index 34.3, $0.66/1M tokens
Qwen3 VL 8B (Reasoning) (Alibaba) — Intelligence Index 8.2, $0.66/1M tokens
Qwen3 8B (Reasoning) (Alibaba) — Intelligence Index 7.3, $0.66/1M tokens
GPT-5 mini (Medium) (OpenAI) — Intelligence Index 20.6, $0.688/1M tokens
GPT-5.1 Codex mini (High) (OpenAI) — Intelligence Index 20.4, $0.688/1M tokens
Qwen3.5 35B A3B (Reasoning) (Alibaba) — Intelligence Index 19.3, $0.688/1M tokens
GPT-5 mini (High) (OpenAI) — Intelligence Index 16.8, $0.688/1M tokens
Qwen3.5 35B A3B (Non-reasoning) (Alibaba) — Intelligence Index 15.1, $0.688/1M tokens
GPT-5 mini (Minimal) (OpenAI) — Intelligence Index 9.9, $0.688/1M tokens
Qwen3.7 Plus (Alibaba) — Intelligence Index 25.2, $0.7/1M tokens
GPT-4.1 mini (OpenAI) — Intelligence Index 10.2, $0.7/1M tokens
Qwen3 VL 235B A22B Instruct (Alibaba) — Intelligence Index 9.9, $0.7/1M tokens
Hermes 3 - Llama-3.1 70B (Nous Research) — Intelligence Index 6.0, $0.7/1M tokens
Llama 3.3 Instruct 70B (Meta) — Intelligence Index 7.7, $0.712/1M tokens
QwQ 32B (Alibaba) — Intelligence Index 9.5, $0.745/1M tokens
Qwen3 235B A22B 2507 (Reasoning) (Alibaba) — Intelligence Index 12.7, $0.747/1M tokens
Qwen3 30B A3B 2507 (Reasoning) (Alibaba) — Intelligence Index 9.8, $0.75/1M tokens
Qwen3 VL 30B A3B (Reasoning) (Alibaba) — Intelligence Index 9.5, $0.75/1M tokens
Mistral Large 3 (Mistral) — Intelligence Index 9.3, $0.75/1M tokens
Magistral Small 1.2 (Mistral) — Intelligence Index 8.6, $0.75/1M tokens
Qwen3 30B A3B (Reasoning) (Alibaba) — Intelligence Index 7.6, $0.75/1M tokens
GPT-3.5 Turbo (OpenAI) — Intelligence Index 5.5, $0.75/1M tokens
Mistral Medium 3 (Mistral) — Intelligence Index 9.0, $0.8/1M tokens
DeepSeek R1 Distill Llama 70B (DeepSeek) — Intelligence Index 7.9, $0.8/1M tokens
Qwen3.5 27B (Reasoning) (Alibaba) — Intelligence Index 22.9, $0.825/1M tokens
Qwen3.5 27B (Non-reasoning) (Alibaba) — Intelligence Index 19.4, $0.825/1M tokens
DeepSeek V3.1 (Non-reasoning) (DeepSeek) — Intelligence Index 13.7, $0.84/1M tokens
Qwen3.6 35B A3B (Reasoning) (Alibaba) — Intelligence Index 18.2, $0.844/1M tokens
Qwen3.6 35B A3B (Non-reasoning) (Alibaba) — Intelligence Index 15.2, $0.844/1M tokens
Gemini 3.5 Flash-Lite (Google) — Intelligence Index 22.2, $0.85/1M tokens
Ling-2.6-1T (InclusionAI) — Intelligence Index 17.0, $0.85/1M tokens
Ring-2.6-1T (InclusionAI) — Intelligence Index 16.6, $0.85/1M tokens
Nova 2.0 Omni (Medium) (Amazon) — Intelligence Index 13.6, $0.85/1M tokens
Nova 2.0 Lite (High) (Amazon) — Intelligence Index 13.4, $0.85/1M tokens
Gemini 2.5 Flash (Reasoning) (Google) — Intelligence Index 13.1, $0.85/1M tokens
Nova 2.0 Lite (Medium) (Amazon) — Intelligence Index 12.5, $0.85/1M tokens
Nova 2.0 Lite (Low) (Amazon) — Intelligence Index 11.8, $0.85/1M tokens
Nova 2.0 Omni (Low) (Amazon) — Intelligence Index 11.1, $0.85/1M tokens
Gemini 2.5 Flash (Non-reasoning) (Google) — Intelligence Index 9.9, $0.85/1M tokens
Nova 2.0 Lite (Non-reasoning) (Amazon) — Intelligence Index 8.7, $0.85/1M tokens
Nova 2.0 Omni (Non-reasoning) (Amazon) — Intelligence Index 8.2, $0.85/1M tokens
DeepSeek V3.1 (Reasoning) (DeepSeek) — Intelligence Index 13.5, $0.855/1M tokens
Quasar 438B (Max, Based on GLM-5.2) (Multiverse Computing) — Intelligence Index 26.7, $0.9/1M tokens
Qwen3 Coder 30B A3B Instruct (Alibaba) — Intelligence Index 9.6, $0.9/1M tokens
GLM-4.5V (Reasoning) (Z AI) — Intelligence Index 7.6, $0.9/1M tokens
GLM-4.5V (Non-reasoning) (Z AI) — Intelligence Index 6.7, $0.9/1M tokens
GLM-4.6 (Reasoning) (Z AI) — Intelligence Index 18.5, $0.963/1M tokens
MiniMax M1 80k (MiniMax) — Intelligence Index 11.7, $0.963/1M tokens
Apodex 1.1 (Apodex) — Intelligence Index 26.4, $0.975/1M tokens
GLM-4.6 (Non-reasoning) (Z AI) — Intelligence Index 14.9, $0.981/1M tokens
GLM-4.7 (Reasoning) (Z AI) — Intelligence Index 22.2, $1.0/1M tokens
GLM-4.7 (Non-reasoning) (Z AI) — Intelligence Index 17.4, $1.0/1M tokens
Kimi K2 (Kimi) — Intelligence Index 12.7, $1.002/1M tokens
Nemotron 3 Ultra 550B A55B (Reasoning) (NVIDIA) — Intelligence Index 22.9, $1.075/1M tokens
Kimi K2 Thinking (Kimi) — Intelligence Index 22.0, $1.075/1M tokens
Kimi K2 0905 (Kimi) — Intelligence Index 15.3, $1.075/1M tokens
Qwen3.5 122B A10B (Non-reasoning) (Alibaba) — Intelligence Index 17.7, $1.1/1M tokens
Qwen3.5 122B A10B (Reasoning) (Alibaba) — Intelligence Index 15.6, $1.1/1M tokens
Qwen3.8 27B (Xhigh) (Alibaba) — Intelligence Index 33.7, $1.125/1M tokens
Qwen3.8 27B (Medium) (Alibaba) — Intelligence Index 27.6, $1.125/1M tokens
Qwen3.6 Plus (Alibaba) — Intelligence Index 27.0, $1.125/1M tokens
Gemini 3 Flash Preview (Reasoning) (Google) — Intelligence Index 26.3, $1.125/1M tokens
Qwen3.8 27B (Low) (Alibaba) — Intelligence Index 26.2, $1.125/1M tokens
Qwen3.8 27B (Non-reasoning) (Alibaba) — Intelligence Index 20.2, $1.125/1M tokens
Gemini 3 Flash Preview (Non-reasoning) (Google) — Intelligence Index 17.9, $1.125/1M tokens
Kimi K2.5 (Reasoning) (Kimi) — Intelligence Index 23.5, $1.137/1M tokens
Llama 3 Instruct 70B (Meta) — Intelligence Index 5.5, $1.175/1M tokens
Kimi K2.5 (Non-reasoning) (Kimi) — Intelligence Index 19.4, $1.2/1M tokens
Qwen3 235B A22B (Non-reasoning) (Alibaba) — Intelligence Index 8.3, $1.225/1M tokens
Grok Build 0.1 0616 (SpaceXAI) — Intelligence Index 27.2, $1.25/1M tokens
Qwen3 VL 235B A22B (Reasoning) (Alibaba) — Intelligence Index 13.4, $1.3/1M tokens
Qwen3 14B (Reasoning) (Alibaba) — Intelligence Index 8.2, $1.313/1M tokens
Apertus 70B Instruct (Swiss AI Initiative) — Intelligence Index 5.1, $1.345/1M tokens
Qwen3.5 397B A17B (Non-reasoning) (Alibaba) — Intelligence Index 21.4, $1.35/1M tokens
Qwen3.6 27B (Reasoning) (Alibaba) — Intelligence Index 21.4, $1.35/1M tokens
Qwen3.6 27B (Non-reasoning) (Alibaba) — Intelligence Index 19.8, $1.35/1M tokens
Qwen3.5 397B A17B (Reasoning) (Alibaba) — Intelligence Index 18.4, $1.35/1M tokens
Nova Pro (Amazon) — Intelligence Index 7.0, $1.4/1M tokens
Step 5 Preview (StepFun) — Intelligence Index 43.7, $1.425/1M tokens
Gemini 3.8 Flash (High) (Google) — Intelligence Index 40.9, $1.5/1M tokens (클릭: 관련 논문)
Gemini 3.8 Flash (Medium) (Google) — Intelligence Index 39.8, $1.5/1M tokens
Gemini 3.7 Flash (Medium) (Google) — Intelligence Index 39.6, $1.5/1M tokens
Gemini 3.7 Flash (High) (Google) — Intelligence Index 39.1, $1.5/1M tokens (클릭: 관련 논문)
Gemini 3.7 Flash (Low) (Google) — Intelligence Index 36.9, $1.5/1M tokens
Gemini 3.6 Flash (High) (Google) — Intelligence Index 34.0, $1.5/1M tokens
Gemini 3.8 Flash (Low) (Google) — Intelligence Index 33.5, $1.5/1M tokens
Qwen3.5 Omni Plus (Alibaba) — Intelligence Index 20.4, $1.5/1M tokens
Hermes 4 - Llama-3.1 405B (Reasoning) (Nous Research) — Intelligence Index 7.5, $1.5/1M tokens
Hermes 4 - Llama-3.1 405B (Non-reasoning) (Nous Research) — Intelligence Index 7.4, $1.5/1M tokens
GLM-5 (Reasoning) (Z AI) — Intelligence Index 27.9, $1.55/1M tokens
GLM-5 (Non-reasoning) (Z AI) — Intelligence Index 21.8, $1.55/1M tokens
Grok 4.20 0309 v2 (Reasoning) (SpaceXAI) — Intelligence Index 25.7, $1.563/1M tokens
Grok 4.3 (High) (SpaceXAI) — Intelligence Index 24.9, $1.563/1M tokens
Grok 4.3 (Medium) (SpaceXAI) — Intelligence Index 24.8, $1.563/1M tokens
Grok 4.3 (Low) (SpaceXAI) — Intelligence Index 24.3, $1.563/1M tokens
Grok 4.20 0309 v2 (Non-reasoning) (SpaceXAI) — Intelligence Index 14.2, $1.563/1M tokens
Grok 4.3 (Non-reasoning) (SpaceXAI) — Intelligence Index 14.0, $1.563/1M tokens
GPT-5.4 mini (Xhigh) (OpenAI) — Intelligence Index 24.1, $1.688/1M tokens
GPT-5.4 mini (Medium) (OpenAI) — Intelligence Index 19.7, $1.688/1M tokens
GPT-5.4 mini (Non-reasoning) (OpenAI) — Intelligence Index 11.1, $1.688/1M tokens
Kimi K2.6 (Reasoning) (Kimi) — Intelligence Index 27.0, $1.712/1M tokens
Kimi K2.7 Code (Kimi) — Intelligence Index 25.8, $1.712/1M tokens
Kimi K2.6 (Non-reasoning) (Kimi) — Intelligence Index 23.6, $1.712/1M tokens
Inkling (Xhigh) (Thinking Machines) — Intelligence Index 25.0, $1.762/1M tokens
DeepSeek R1 0528 (May '25) (DeepSeek) — Intelligence Index 13.1, $1.763/1M tokens
DeepSeek V3.1 Terminus (Reasoning) (DeepSeek) — Intelligence Index 14.8, $1.914/1M tokens
o4-mini (High) (OpenAI) — Intelligence Index 16.7, $1.925/1M tokens
o3-mini (OpenAI) — Intelligence Index 12.5, $1.925/1M tokens
o3-mini (High) (OpenAI) — Intelligence Index 11.0, $1.925/1M tokens
DeepSeek V4 Pro 0813 (Max) (DeepSeek) — Intelligence Index 36.0, $1.98/1M tokens
DeepSeek V4 Pro 0813 (Non-reasoning) (DeepSeek) — Intelligence Index 20.4, $1.98/1M tokens
GLM-5.1 (Reasoning) (Z AI) — Intelligence Index 26.1, $1.981/1M tokens
Muse Spark 1.3 (Max) (Meta) — Intelligence Index 48.1, $2.0/1M tokens (클릭: 관련 논문)
Muse Spark 1.3 (Xhigh) (Meta) — Intelligence Index 45.1, $2.0/1M tokens (클릭: 관련 논문)
Muse Spark 1.2 (Xhigh) (Meta) — Intelligence Index 39.6, $2.0/1M tokens
Muse Spark 1.1 (Xhigh) (Meta) — Intelligence Index 33.7, $2.0/1M tokens
Claude 4.5 Haiku (Reasoning) (Anthropic) — Intelligence Index 16.9, $2.0/1M tokens
Claude 4.5 Haiku (Non-reasoning) (Anthropic) — Intelligence Index 15.4, $2.0/1M tokens
Mistral Large 4 Preview (Mistral) — Intelligence Index 38.4, $2.065/1M tokens
GLM-5.1 (Non-reasoning) (Z AI) — Intelligence Index 24.2, $2.135/1M tokens
GLM-5.3 (Max) (Z AI) — Intelligence Index 44.8, $2.15/1M tokens
GLM-5.3 (Low) (Z AI) — Intelligence Index 34.3, $2.15/1M tokens
GLM-5.2 (Max) (Z AI) — Intelligence Index 33.7, $2.15/1M tokens
GLM-5.2 (Non-reasoning) (Z AI) — Intelligence Index 22.4, $2.15/1M tokens
Qwen3 Max Thinking (Preview) (Alibaba) — Intelligence Index 16.3, $2.4/1M tokens
Qwen3 Max (Alibaba) — Intelligence Index 15.6, $2.4/1M tokens
Qwen3 Max (Preview) (Alibaba) — Intelligence Index 12.6, $2.4/1M tokens
DeepSeek R1 (Jan '25) (DeepSeek) — Intelligence Index 11.4, $2.5/1M tokens
Qwen3 235B A22B (Reasoning) (Alibaba) — Intelligence Index 9.5, $2.625/1M tokens
Qwen3.6 Max Preview (Alibaba) — Intelligence Index 28.4, $2.925/1M tokens
Grok 4.7 (Xhigh) (SpaceXAI) — Intelligence Index 46.4, $3.0/1M tokens
Grok 4.7 (High) (SpaceXAI) — Intelligence Index 46.3, $3.0/1M tokens
Qwen3.8 Max (0902) (Alibaba) — Intelligence Index 45.4, $3.0/1M tokens (클릭: 관련 논문)
Grok 4.6 (High) (SpaceXAI) — Intelligence Index 44.3, $3.0/1M tokens (클릭: 관련 논문)
Grok 4.6 (Xhigh) (SpaceXAI) — Intelligence Index 44.2, $3.0/1M tokens (클릭: 관련 논문)
Grok 4.6 (Medium) (SpaceXAI) — Intelligence Index 42.8, $3.0/1M tokens
Grok 4.7 (Low) (SpaceXAI) — Intelligence Index 42.2, $3.0/1M tokens
Qwen3.8 Max (Alibaba) — Intelligence Index 40.2, $3.0/1M tokens
Qwen3.8 2.4T A95B (Alibaba) — Intelligence Index 39.9, $3.0/1M tokens
Grok 4.5 (High) (SpaceXAI) — Intelligence Index 38.8, $3.0/1M tokens
Grok 4.6 (Low) (SpaceXAI) — Intelligence Index 35.1, $3.0/1M tokens
Grok 4.20 0309 (Reasoning) (SpaceXAI) — Intelligence Index 25.2, $3.0/1M tokens
Grok 4.20 0309 (Non-reasoning) (SpaceXAI) — Intelligence Index 14.6, $3.0/1M tokens
Mistral Medium 3.5 (Mistral) — Intelligence Index 14.2, $3.0/1M tokens
Qwen3 Coder 480B A35B Instruct (Alibaba) — Intelligence Index 11.9, $3.0/1M tokens
Mistral Large 2 (Jul '24) (Mistral) — Intelligence Index 6.8, $3.0/1M tokens
Gemini 3.5 Flash (Medium) (Google) — Intelligence Index 33.6, $3.375/1M tokens
Gemini 3.5 Flash (High) (Google) — Intelligence Index 32.6, $3.375/1M tokens
Gemini 3.5 Flash (Minimal) (Google) — Intelligence Index 23.8, $3.375/1M tokens
GPT-5 Codex (High) (OpenAI) — Intelligence Index 24.9, $3.438/1M tokens
GPT-5.1 (High) (OpenAI) — Intelligence Index 24.7, $3.438/1M tokens
GPT-5.1 Codex (High) (OpenAI) — Intelligence Index 23.7, $3.438/1M tokens
GPT-5 (High) (OpenAI) — Intelligence Index 23.0, $3.438/1M tokens
GPT-5 (Medium) (OpenAI) — Intelligence Index 22.9, $3.438/1M tokens
GPT-5 (Low) (OpenAI) — Intelligence Index 20.8, $3.438/1M tokens
Gemini 2.5 Pro (Google) — Intelligence Index 16.1, $3.438/1M tokens
Gemini 2.5 Pro Preview (May' 25) (Google) — Intelligence Index 14.5, $3.438/1M tokens
Nova 2.0 Pro Preview (Medium) (Amazon) — Intelligence Index 14.2, $3.438/1M tokens
GPT-5.1 (Non-reasoning) (OpenAI) — Intelligence Index 13.3, $3.438/1M tokens
Nova 2.0 Pro Preview (Low) (Amazon) — Intelligence Index 12.8, $3.438/1M tokens
GPT-5 (Minimal) (OpenAI) — Intelligence Index 11.4, $3.438/1M tokens
Nova 2.0 Pro Preview (Non-reasoning) (Amazon) — Intelligence Index 10.0, $3.438/1M tokens
o3 (OpenAI) — Intelligence Index 20.2, $3.5/1M tokens
GPT-4.1 (OpenAI) — Intelligence Index 12.7, $3.5/1M tokens
Jamba 1.5 Large (AI21 Labs) — Intelligence Index 6.0, $3.5/1M tokens
Qwen3.7 Max (Alibaba) — Intelligence Index 29.5, $3.75/1M tokens
Claude Sonnet 5.5 (Max, Default Fallback) (Anthropic) — Intelligence Index 56.0, $4.0/1M tokens (클릭: 관련 논문)
Gemini 4 Argon (High) (Google) — Intelligence Index 52.6, $4.0/1M tokens (클릭: 관련 논문)
Claude Sonnet 5.5 (Xhigh, Default Fallback) (Anthropic) — Intelligence Index 51.9, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (Max) (OpenAI) — Intelligence Index 51.8, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (Xhigh) (OpenAI) — Intelligence Index 51.0, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (High) (OpenAI) — Intelligence Index 50.2, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (Medium) (OpenAI) — Intelligence Index 47.8, $4.0/1M tokens (클릭: 관련 논문)
GPT-6 Sol (Max) (OpenAI) — Intelligence Index 47.6, $4.0/1M tokens (클릭: 관련 논문)
Claude Sonnet 5.5 (High, Default Fallback) (Anthropic) — Intelligence Index 46.8, $4.0/1M tokens
GPT-6 Sol (Xhigh) (OpenAI) — Intelligence Index 44.2, $4.0/1M tokens
GPT-6 Sol (High) (OpenAI) — Intelligence Index 42.4, $4.0/1M tokens
GPT-6.1 Sol (Low) (OpenAI) — Intelligence Index 42.1, $4.0/1M tokens
Claude Sonnet 5.5 (Medium, Default Fallback) (Anthropic) — Intelligence Index 40.8, $4.0/1M tokens
GPT-6 Sol (Medium) (OpenAI) — Intelligence Index 39.8, $4.0/1M tokens
Claude Sonnet 5 (Max) (Anthropic) — Intelligence Index 38.2, $4.0/1M tokens
Claude Sonnet 5.5 (Low, Default Fallback) (Anthropic) — Intelligence Index 35.9, $4.0/1M tokens
Claude Sonnet 5 (Xhigh) (Anthropic) — Intelligence Index 34.4, $4.0/1M tokens
GPT-6 Sol (Low) (OpenAI) — Intelligence Index 34.2, $4.0/1M tokens
Claude Sonnet 5 (High) (Anthropic) — Intelligence Index 31.7, $4.0/1M tokens
GPT-6 Sol (Non-reasoning) (OpenAI) — Intelligence Index 28.5, $4.0/1M tokens
Claude Sonnet 5 (Medium) (Anthropic) — Intelligence Index 28.1, $4.0/1M tokens
Claude Sonnet 5 (Low) (Anthropic) — Intelligence Index 24.3, $4.0/1M tokens
Claude Sonnet 5 (Non-reasoning, High) (Anthropic) — Intelligence Index 23.2, $4.0/1M tokens
GPT-4o (Nov '24) (OpenAI) — Intelligence Index 8.4, $4.375/1M tokens
GPT-4o (Aug '24) (OpenAI) — Intelligence Index 7.7, $4.375/1M tokens
Command A (Cohere) — Intelligence Index 7.0, $4.375/1M tokens
GPT-5.6 Terra (Max) (OpenAI) — Intelligence Index 42.1, $4.5/1M tokens (클릭: 관련 논문)
GPT-5.6 Terra (Xhigh) (OpenAI) — Intelligence Index 38.0, $4.5/1M tokens
GPT-5.6 Terra (High) (OpenAI) — Intelligence Index 34.2, $4.5/1M tokens
GPT-5.6 Terra (Medium) (OpenAI) — Intelligence Index 30.1, $4.5/1M tokens
Gemini 3.1 Pro Preview (Google) — Intelligence Index 29.7, $4.5/1M tokens
Gemini 3 Pro Preview (High) (Google) — Intelligence Index 28.0, $4.5/1M tokens
GPT-5.6 Terra (Low) (OpenAI) — Intelligence Index 27.5, $4.5/1M tokens
Gemini 3 Pro Preview (Low) (Google) — Intelligence Index 22.3, $4.5/1M tokens
GPT-5.6 Terra (Non-reasoning) (OpenAI) — Intelligence Index 20.8, $4.5/1M tokens
GPT-5.3 Codex (Xhigh) (OpenAI) — Intelligence Index 32.5, $4.813/1M tokens
GPT-5.2 (Xhigh) (OpenAI) — Intelligence Index 30.4, $4.813/1M tokens
GPT-5.2 Codex (Xhigh) (OpenAI) — Intelligence Index 28.5, $4.813/1M tokens
GPT-5.2 (Medium) (OpenAI) — Intelligence Index 26.5, $4.813/1M tokens
GPT-5.2 (Non-reasoning) (OpenAI) — Intelligence Index 17.0, $4.813/1M tokens
GPT-5.4 (Xhigh) (OpenAI) — Intelligence Index 39.0, $5.625/1M tokens
GPT-5.4 (Low) (OpenAI) — Intelligence Index 27.6, $5.625/1M tokens
GPT-5.4 (Non-reasoning) (OpenAI) — Intelligence Index 18.2, $5.625/1M tokens
Kimi K3 (Max) (Kimi) — Intelligence Index 43.6, $6.0/1M tokens (클릭: 관련 논문)
Kimi K3 (Low) (Kimi) — Intelligence Index 30.1, $6.0/1M tokens
Claude Sonnet 4.6 (Max) (Anthropic) — Intelligence Index 30.1, $6.0/1M tokens
Claude Sonnet 4.6 (Non-reasoning, High) (Anthropic) — Intelligence Index 24.7, $6.0/1M tokens
Claude Sonnet 4.6 (Non-reasoning, Low) (Anthropic) — Intelligence Index 23.3, $6.0/1M tokens
Grok 4 (SpaceXAI) — Intelligence Index 22.5, $6.0/1M tokens
Claude 4.5 Sonnet (Reasoning) (Anthropic) — Intelligence Index 20.7, $6.0/1M tokens
Claude 4.5 Sonnet (Non-reasoning) (Anthropic) — Intelligence Index 19.3, $6.0/1M tokens
Claude 3.7 Sonnet (Non-reasoning) (Anthropic) — Intelligence Index 15.3, $6.0/1M tokens
Claude 3.5 Sonnet (Oct '24) (Anthropic) — Intelligence Index 7.9, $6.0/1M tokens
Claude 3.5 Sonnet (June '24) (Anthropic) — Intelligence Index 7.2, $6.0/1M tokens
Mistral Large (Feb '24) (Mistral) — Intelligence Index 5.8, $6.0/1M tokens
GPT-4o (May '24) (OpenAI) — Intelligence Index 7.3, $7.5/1M tokens
Claude Opus 5.5 (Max, Default Fallback) (Anthropic) — Intelligence Index 57.6, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (Xhigh, Default Fallback) (Anthropic) — Intelligence Index 56.0, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (High, Default Fallback) (Anthropic) — Intelligence Index 53.6, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (Medium, Default Fallback) (Anthropic) — Intelligence Index 51.2, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Max) (OpenAI) — Intelligence Index 47.0, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Xhigh) (OpenAI) — Intelligence Index 44.0, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (High) (OpenAI) — Intelligence Index 42.3, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (Low, Default Fallback) (Anthropic) — Intelligence Index 42.3, $8.0/1M tokens
GPT-5.6 Sol (Medium) (OpenAI) — Intelligence Index 39.2, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Low) (OpenAI) — Intelligence Index 33.5, $8.0/1M tokens
GPT-5.6 Sol (Non-reasoning) (OpenAI) — Intelligence Index 28.3, $8.0/1M tokens
Grok 3 (SpaceXAI) — Intelligence Index 12.1, $8.0/1M tokens
Claude Opus 5 (Max) (Anthropic) — Intelligence Index 50.8, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (Xhigh) (Anthropic) — Intelligence Index 49.7, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (High) (Anthropic) — Intelligence Index 48.1, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (Medium) (Anthropic) — Intelligence Index 44.8, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 4.8 (Max) (Anthropic) — Intelligence Index 41.8, $10.0/1M tokens
Claude Opus 4.7 (Max) (Anthropic) — Intelligence Index 40.7, $10.0/1M tokens
Claude Opus 5 (Low) (Anthropic) — Intelligence Index 39.4, $10.0/1M tokens
Claude Opus 4.6 (Max) (Anthropic) — Intelligence Index 31.9, $10.0/1M tokens
Claude Opus 4.7 (Non-reasoning, High) (Anthropic) — Intelligence Index 30.9, $10.0/1M tokens
Claude Opus 4.5 (Reasoning) (Anthropic) — Intelligence Index 29.1, $10.0/1M tokens
Claude Opus 4.6 (Non-reasoning, High) (Anthropic) — Intelligence Index 26.4, $10.0/1M tokens
Claude Opus 4.5 (Non-reasoning) (Anthropic) — Intelligence Index 23.7, $10.0/1M tokens
GPT-5.5 (Xhigh) (OpenAI) — Intelligence Index 38.4, $11.25/1M tokens
GPT-5.5 (High) (OpenAI) — Intelligence Index 37.0, $11.25/1M tokens
GPT-5.5 (Medium) (OpenAI) — Intelligence Index 33.8, $11.25/1M tokens
GPT-5.5 (Low) (OpenAI) — Intelligence Index 30.7, $11.25/1M tokens
GPT-5.5 Instant (June 2026) (OpenAI) — Intelligence Index 26.0, $11.25/1M tokens
GPT-5.5 (Non-reasoning) (OpenAI) — Intelligence Index 23.2, $11.25/1M tokens
GPT-5.5 Instant (May 2026) (OpenAI) — Intelligence Index 22.7, $11.25/1M tokens
GPT-4 Turbo (OpenAI) — Intelligence Index 7.0, $15.0/1M tokens
Claude Fable 5.1 (Max, Default Fallback) (Anthropic) — Intelligence Index 53.4, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (Xhigh, Default Fallback) (Anthropic) — Intelligence Index 53.2, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Max) (OpenAI) — Intelligence Index 52.7, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Xhigh) (OpenAI) — Intelligence Index 52.4, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (High, Default Fallback) (Anthropic) — Intelligence Index 51.2, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (High) (OpenAI) — Intelligence Index 50.9, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5 (Max, Opus 4.8 Fallback) (Anthropic) — Intelligence Index 49.6, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Medium) (OpenAI) — Intelligence Index 49.6, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (Medium, Default Fallback) (Anthropic) — Intelligence Index 48.9, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (Low, Default Fallback) (Anthropic) — Intelligence Index 46.8, $20.0/1M tokens
GPT-6 Astra (Low) (OpenAI) — Intelligence Index 45.8, $20.0/1M tokens
o1 (OpenAI) — Intelligence Index 15.2, $26.25/1M tokens
o1-preview (OpenAI) — Intelligence Index 11.4, $28.875/1M tokens
Claude 4.1 Opus (Reasoning) (Anthropic) — Intelligence Index 22.8, $30.0/1M tokens
Claude 4 Opus (Reasoning) (Anthropic) — Intelligence Index 20.6, $30.0/1M tokens
Claude 4.1 Opus (Non-reasoning) (Anthropic) — Intelligence Index 18.6, $30.0/1M tokens
Claude 4 Opus (Non-reasoning) (Anthropic) — Intelligence Index 16.6, $30.0/1M tokens
Claude 3 Opus (Anthropic) — Intelligence Index 8.7, $30.0/1M tokens
o3-pro (OpenAI) — Intelligence Index 21.9, $35.0/1M tokens
GPT-4 (OpenAI) — Intelligence Index 6.7, $37.5/1M tokens
o1-pro (OpenAI) — Intelligence Index 12.4, $262.5/1M tokens
Llama 3.1 Instruct 8B
Gemma 4 E4B
Granite 4.2 3B
Qwen3.5 4B
Hy3-preview
Ling-3.0-flash-VL
MiMo-V2.6-Flash
Claude Haiku 5.5
MiMo-V2.6-Pro
Muse Spark 1.3
Claude Sonnet 5.5
Claude Opus 5.5
Coding Index ↑
20
40
60
80
$0.1
$1
$10
1M 토큰당 가격
(USD · 로그 축) →
Llama 3.1 Instruct 8B (Meta) — Coding Index 5.4, $0.028/1M tokens (클릭: 관련 논문)
Granite 4.2 3B (IBM) — Coding Index 17.5, $0.052/1M tokens
Qwen3.5 4B (Reasoning) (Alibaba) — Coding Index 22.6, $0.06/1M tokens (클릭: 관련 논문)
Qwen3.5 4B (Non-reasoning) (Alibaba) — Coding Index 20.3, $0.06/1M tokens
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA) — Coding Index 14.4, $0.088/1M tokens
Nemotron 3.5 Lightning (NVIDIA) — Coding Index 26.8, $0.095/1M tokens (클릭: 관련 논문)
gpt-oss-20b (High) (OpenAI) — Coding Index 20.7, $0.098/1M tokens
Ministral 3 3B (Mistral) — Coding Index 4.8, $0.1/1M tokens
Mistral Small 3.2 (Mistral) — Coding Index 12.5, $0.106/1M tokens
Granite 4.2 8B (IBM) — Coding Index 22.4, $0.107/1M tokens
Ling-3.0-flash-VL (InclusionAI) — Coding Index 57.0, $0.111/1M tokens
Ling-3.0-flash-Fin (InclusionAI) — Coding Index 55.6, $0.111/1M tokens
Ling 3.0 Flash (InclusionAI) — Coding Index 50.6, $0.111/1M tokens
Mistral Small 3.1 (Mistral) — Coding Index 26.3, $0.125/1M tokens
Gemma 4 12B (Reasoning) (Google) — Coding Index 31.0, $0.15/1M tokens
Ministral 3 8B (Mistral) — Coding Index 9.7, $0.15/1M tokens
Qwen3.5 9B (Reasoning) (Alibaba) — Coding Index 28.7, $0.151/1M tokens
DeepSeek V4 Flash 0420 (Max) (DeepSeek) — Coding Index 56.2, $0.168/1M tokens
DeepSeek V4 Flash 0420 (High) (DeepSeek) — Coding Index 52.0, $0.168/1M tokens
Gemma 4 26B A4B (Reasoning) (Google) — Coding Index 39.3, $0.168/1M tokens
MiMo-V2.5 (Xiaomi) — Coding Index 56.8, $0.175/1M tokens
GPT-4.1 nano (OpenAI) — Coding Index 11.1, $0.175/1M tokens
Qwen3.5 9B (Non-reasoning) (Alibaba) — Coding Index 23.5, $0.19/1M tokens
Ministral 3 14B (Mistral) — Coding Index 14.4, $0.2/1M tokens
Gemma 4 31B (Non-reasoning) (Google) — Coding Index 33.2, $0.224/1M tokens
Qwen3.8-Flash-Next (Alibaba) — Coding Index 73.1, $0.23/1M tokens (클릭: 관련 논문)
GLM 5.3 Flash (Z AI) — Coding Index 71.5, $0.237/1M tokens
Hy3 (Tencent) — Coding Index 58.8, $0.241/1M tokens
gpt-oss-120b (Low) (OpenAI) — Coding Index 21.2, $0.249/1M tokens
gpt-oss-120b (High) (OpenAI) — Coding Index 30.4, $0.261/1M tokens
Mistral Small 4 (Reasoning) (Mistral) — Coding Index 26.6, $0.262/1M tokens
Solar Pro 3 (Upstage) — Coding Index 16.2, $0.262/1M tokens
GPT-4o mini (OpenAI) — Coding Index 11.4, $0.262/1M tokens
Qwen3 32B (Reasoning) (Alibaba) — Coding Index 15.3, $0.28/1M tokens
Granite 4.2 30B (IBM) — Coding Index 29.9, $0.282/1M tokens
Llama 4 Scout (Meta) — Coding Index 8.2, $0.313/1M tokens
DeepSeek V3.2 (Reasoning) (DeepSeek) — Coding Index 44.2, $0.315/1M tokens
Celeris-1 (Celeris) — Coding Index 14.4, $0.325/1M tokens
Mercury 2 (Inception) — Coding Index 31.1, $0.375/1M tokens
Trinity Large Thinking (Arcee AI) — Coding Index 25.8, $0.388/1M tokens
DeepSeek V3 0324 (DeepSeek) — Coding Index 21.2, $0.405/1M tokens
Llama 4 Maverick (Meta) — Coding Index 16.3, $0.405/1M tokens
Qwen3 Next 80B A3B (Reasoning) (Alibaba) — Coding Index 17.4, $0.412/1M tokens
Step 3.7 Flash (StepFun) — Coding Index 39.6, $0.438/1M tokens
GPT-5.6 Luna (Max) (OpenAI) — Coding Index 71.4, $0.45/1M tokens
GPT-5.6 Luna (Xhigh) (OpenAI) — Coding Index 68.6, $0.45/1M tokens
GPT-5.6 Luna (High) (OpenAI) — Coding Index 63.3, $0.45/1M tokens
GPT-5.6 Luna (Medium) (OpenAI) — Coding Index 50.7, $0.45/1M tokens
GPT-5.6 Luna (Low) (OpenAI) — Coding Index 44.2, $0.45/1M tokens
GPT-5.6 Luna (Non-reasoning) (OpenAI) — Coding Index 39.3, $0.45/1M tokens
Nemotron 3 Super 120B A12B (Reasoning) (NVIDIA) — Coding Index 37.7, $0.45/1M tokens
Nemotron 3 Nano Omni 30B A3B Reasoning (NVIDIA) — Coding Index 13.8, $0.45/1M tokens
GPT-5.4 nano (Xhigh) (OpenAI) — Coding Index 56.1, $0.463/1M tokens
DeepSeek V3 (Dec '24) (DeepSeek) — Coding Index 23.0, $0.463/1M tokens
KAT Coder Pro V2 (KwaiKAT) — Coding Index 59.5, $0.525/1M tokens
MiniMax-M3 (MiniMax) — Coding Index 58.6, $0.525/1M tokens
Inkling Small (Thinking Machines) — Coding Index 52.9, $0.525/1M tokens
Solar Pro 4 (Upstage) — Coding Index 52.7, $0.525/1M tokens
MiniMax-M2.7 (MiniMax) — Coding Index 52.6, $0.525/1M tokens
LongCat 2.0 (LongCat) — Coding Index 45.3, $0.525/1M tokens
MiMo-V2.5-Pro (Reasoning) (Xiaomi) — Coding Index 60.2, $0.544/1M tokens
DeepSeek V4 Pro 0424 (Max) (DeepSeek) — Coding Index 59.4, $0.544/1M tokens
DeepSeek V4 Pro 0424 (High) (DeepSeek) — Coding Index 58.7, $0.544/1M tokens
Qwen3 Coder Next (Alibaba) — Coding Index 36.2, $0.563/1M tokens
Gemini 3.1 Flash-Lite (Google) — Coding Index 34.7, $0.563/1M tokens
Muse Glimmer (High) (Meta) — Coding Index 49.0, $0.581/1M tokens
DeepSeek V4 Flash 0731 (Max) (DeepSeek) — Coding Index 69.1, $0.66/1M tokens
DeepSeek V4 Flash Vision (Max) (DeepSeek) — Coding Index 65.0, $0.66/1M tokens
Qwen3 8B (Reasoning) (Alibaba) — Coding Index 9.0, $0.66/1M tokens
Qwen3.5 35B A3B (Non-reasoning) (Alibaba) — Coding Index 37.0, $0.688/1M tokens
GPT-5 mini (High) (OpenAI) — Coding Index 15.6, $0.688/1M tokens
Qwen3.7 Plus (Alibaba) — Coding Index 55.9, $0.7/1M tokens
GPT-4.1 mini (OpenAI) — Coding Index 20.2, $0.7/1M tokens
Llama 3.3 Instruct 70B (Meta) — Coding Index 11.9, $0.712/1M tokens
Qwen3 235B A22B 2507 (Reasoning) (Alibaba) — Coding Index 22.1, $0.747/1M tokens
Mistral Large 3 (Mistral) — Coding Index 20.1, $0.75/1M tokens
Magistral Small 1.2 (Mistral) — Coding Index 14.7, $0.75/1M tokens
Qwen3 30B A3B 2507 (Reasoning) (Alibaba) — Coding Index 12.1, $0.75/1M tokens
GPT-3.5 Turbo (OpenAI) — Coding Index 10.7, $0.75/1M tokens
Qwen3.6 35B A3B (Reasoning) (Alibaba) — Coding Index 41.9, $0.844/1M tokens
Qwen3.6 35B A3B (Non-reasoning) (Alibaba) — Coding Index 28.1, $0.844/1M tokens
Gemini 3.5 Flash-Lite (Google) — Coding Index 49.3, $0.85/1M tokens
Ring-2.6-1T (InclusionAI) — Coding Index 42.8, $0.85/1M tokens
Nova 2.0 Lite (High) (Amazon) — Coding Index 23.0, $0.85/1M tokens
Quasar 438B (Max, Based on GLM-5.2) (Multiverse Computing) — Coding Index 61.2, $0.9/1M tokens
GLM-4.6 (Reasoning) (Z AI) — Coding Index 45.8, $0.963/1M tokens
Apodex 1.1 (Apodex) — Coding Index 60.8, $0.975/1M tokens
GLM-4.7 (Reasoning) (Z AI) — Coding Index 45.3, $1.0/1M tokens
Nemotron 3 Ultra 550B A55B (Reasoning) (NVIDIA) — Coding Index 49.3, $1.075/1M tokens
Qwen3.5 122B A10B (Reasoning) (Alibaba) — Coding Index 45.7, $1.1/1M tokens
Qwen3.5 122B A10B (Non-reasoning) (Alibaba) — Coding Index 43.3, $1.1/1M tokens
Qwen3.8 27B (Xhigh) (Alibaba) — Coding Index 68.1, $1.125/1M tokens
Qwen3.8 27B (Low) (Alibaba) — Coding Index 58.2, $1.125/1M tokens
Qwen3.8 27B (Medium) (Alibaba) — Coding Index 56.1, $1.125/1M tokens
Qwen3.6 Plus (Alibaba) — Coding Index 54.5, $1.125/1M tokens
Qwen3.8 27B (Non-reasoning) (Alibaba) — Coding Index 44.6, $1.125/1M tokens
Kimi K2.5 (Reasoning) (Kimi) — Coding Index 46.8, $1.137/1M tokens
Grok Build 0.1 0616 (SpaceXAI) — Coding Index 51.5, $1.25/1M tokens
Qwen3 14B (Reasoning) (Alibaba) — Coding Index 13.8, $1.313/1M tokens
Qwen3.6 27B (Reasoning) (Alibaba) — Coding Index 53.7, $1.35/1M tokens
Qwen3.5 397B A17B (Reasoning) (Alibaba) — Coding Index 48.2, $1.35/1M tokens
Qwen3.6 27B (Non-reasoning) (Alibaba) — Coding Index 46.6, $1.35/1M tokens
Gemini 3.8 Flash (High) (Google) — Coding Index 76.3, $1.5/1M tokens (클릭: 관련 논문)
Gemini 3.7 Flash (High) (Google) — Coding Index 76.1, $1.5/1M tokens (클릭: 관련 논문)
Gemini 3.8 Flash (Medium) (Google) — Coding Index 74.1, $1.5/1M tokens
Gemini 3.8 Flash (Low) (Google) — Coding Index 73.5, $1.5/1M tokens
Gemini 3.7 Flash (Medium) (Google) — Coding Index 71.5, $1.5/1M tokens
Gemini 3.7 Flash (Low) (Google) — Coding Index 71.0, $1.5/1M tokens
Gemini 3.6 Flash (High) (Google) — Coding Index 69.2, $1.5/1M tokens
Grok 4.3 (High) (SpaceXAI) — Coding Index 42.2, $1.563/1M tokens
Grok 4.3 (Non-reasoning) (SpaceXAI) — Coding Index 35.2, $1.563/1M tokens
GPT-5.4 mini (Xhigh) (OpenAI) — Coding Index 56.1, $1.688/1M tokens
Kimi K2.6 (Reasoning) (Kimi) — Coding Index 61.8, $1.712/1M tokens
Kimi K2.7 Code (Kimi) — Coding Index 60.8, $1.712/1M tokens
Inkling (Xhigh) (Thinking Machines) — Coding Index 52.1, $1.762/1M tokens
DeepSeek V3.1 Terminus (Reasoning) (DeepSeek) — Coding Index 43.5, $1.914/1M tokens
o3-mini (High) (OpenAI) — Coding Index 16.3, $1.925/1M tokens
DeepSeek V4 Pro 0813 (Max) (DeepSeek) — Coding Index 68.8, $1.98/1M tokens
GLM-5.1 (Reasoning) (Z AI) — Coding Index 55.8, $1.981/1M tokens
Muse Spark 1.3 (Xhigh) (Meta) — Coding Index 76.5, $2.0/1M tokens (클릭: 관련 논문)
Muse Spark 1.3 (Max) (Meta) — Coding Index 75.8, $2.0/1M tokens (클릭: 관련 논문)
Muse Spark 1.2 (Xhigh) (Meta) — Coding Index 72.2, $2.0/1M tokens
Muse Spark 1.1 (Xhigh) (Meta) — Coding Index 71.3, $2.0/1M tokens
Claude 4.5 Haiku (Reasoning) (Anthropic) — Coding Index 43.9, $2.0/1M tokens
GLM-5.3 (Max) (Z AI) — Coding Index 74.8, $2.15/1M tokens
GLM-5.2 (Max) (Z AI) — Coding Index 68.8, $2.15/1M tokens
GLM-5.2 (Non-reasoning) (Z AI) — Coding Index 46.5, $2.15/1M tokens
DeepSeek R1 (Jan '25) (DeepSeek) — Coding Index 24.6, $2.5/1M tokens
Grok 4.6 (High) (SpaceXAI) — Coding Index 76.8, $3.0/1M tokens (클릭: 관련 논문)
Qwen3.8 Max (0902) (Alibaba) — Coding Index 76.2, $3.0/1M tokens (클릭: 관련 논문)
Grok 4.6 (Xhigh) (SpaceXAI) — Coding Index 75.9, $3.0/1M tokens (클릭: 관련 논문)
Grok 4.6 (Medium) (SpaceXAI) — Coding Index 74.4, $3.0/1M tokens
Grok 4.5 (High) (SpaceXAI) — Coding Index 72.4, $3.0/1M tokens
Qwen3.8 2.4T A95B (Alibaba) — Coding Index 71.9, $3.0/1M tokens
Qwen3.8 Max (Alibaba) — Coding Index 71.8, $3.0/1M tokens
Grok 4.6 (Low) (SpaceXAI) — Coding Index 66.3, $3.0/1M tokens
Mistral Medium 3.5 (Mistral) — Coding Index 46.9, $3.0/1M tokens
Gemini 3.5 Flash (High) (Google) — Coding Index 70.1, $3.375/1M tokens
GPT-5.1 (High) (OpenAI) — Coding Index 49.4, $3.438/1M tokens
GPT-5 (High) (OpenAI) — Coding Index 37.8, $3.438/1M tokens
Nova 2.0 Pro Preview (Medium) (Amazon) — Coding Index 34.0, $3.438/1M tokens
Gemini 2.5 Pro (Google) — Coding Index 33.3, $3.438/1M tokens
Nova 2.0 Pro Preview (Low) (Amazon) — Coding Index 25.9, $3.438/1M tokens
Nova 2.0 Pro Preview (Non-reasoning) (Amazon) — Coding Index 20.9, $3.438/1M tokens
Qwen3.7 Max (Alibaba) — Coding Index 66.0, $3.75/1M tokens
Claude Sonnet 5 (Max) (Anthropic) — Coding Index 71.5, $4.0/1M tokens
Claude Sonnet 5 (Non-reasoning, High) (Anthropic) — Coding Index 66.4, $4.0/1M tokens
GPT-5.6 Terra (Max) (OpenAI) — Coding Index 76.7, $4.5/1M tokens (클릭: 관련 논문)
GPT-5.6 Terra (Xhigh) (OpenAI) — Coding Index 70.6, $4.5/1M tokens
Gemini 3.1 Pro Preview (Google) — Coding Index 68.8, $4.5/1M tokens
GPT-5.6 Terra (High) (OpenAI) — Coding Index 67.1, $4.5/1M tokens
GPT-5.6 Terra (Medium) (OpenAI) — Coding Index 64.7, $4.5/1M tokens
GPT-5.6 Terra (Low) (OpenAI) — Coding Index 58.1, $4.5/1M tokens
GPT-5.6 Terra (Non-reasoning) (OpenAI) — Coding Index 52.3, $4.5/1M tokens
GPT-5.4 (Xhigh) (OpenAI) — Coding Index 71.1, $5.625/1M tokens
Kimi K3 (Max) (Kimi) — Coding Index 76.2, $6.0/1M tokens (클릭: 관련 논문)
Kimi K3 (Low) (Kimi) — Coding Index 72.0, $6.0/1M tokens
Claude Sonnet 4.6 (Max) (Anthropic) — Coding Index 63.0, $6.0/1M tokens
Claude 4.5 Sonnet (Reasoning) (Anthropic) — Coding Index 52.1, $6.0/1M tokens
Claude 3.5 Sonnet (Oct '24) (Anthropic) — Coding Index 30.2, $6.0/1M tokens
Claude 3.5 Sonnet (June '24) (Anthropic) — Coding Index 26.0, $6.0/1M tokens
GPT-4o (May '24) (OpenAI) — Coding Index 24.2, $7.5/1M tokens
GPT-5.6 Sol (Xhigh) (OpenAI) — Coding Index 78.3, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Max) (OpenAI) — Coding Index 77.4, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (High) (OpenAI) — Coding Index 77.2, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Medium) (OpenAI) — Coding Index 76.3, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Low) (OpenAI) — Coding Index 69.7, $8.0/1M tokens
GPT-5.6 Sol (Non-reasoning) (OpenAI) — Coding Index 65.1, $8.0/1M tokens
Claude Opus 5 (Max) (Anthropic) — Coding Index 78.0, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (Xhigh) (Anthropic) — Coding Index 77.0, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (High) (Anthropic) — Coding Index 76.5, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (Medium) (Anthropic) — Coding Index 74.3, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 4.8 (Max) (Anthropic) — Coding Index 74.3, $10.0/1M tokens
Claude Opus 4.7 (Max) (Anthropic) — Coding Index 73.6, $10.0/1M tokens
Claude Opus 5 (Low) (Anthropic) — Coding Index 66.9, $10.0/1M tokens
GPT-5.5 (Xhigh) (OpenAI) — Coding Index 74.9, $11.25/1M tokens
GPT-5.5 (High) (OpenAI) — Coding Index 71.6, $11.25/1M tokens
GPT-5.5 (Medium) (OpenAI) — Coding Index 71.5, $11.25/1M tokens
GPT-5.5 (Low) (OpenAI) — Coding Index 60.9, $11.25/1M tokens
GPT-5.5 (Non-reasoning) (OpenAI) — Coding Index 56.5, $11.25/1M tokens
GPT-5.5 Instant (June 2026) (OpenAI) — Coding Index 39.4, $11.25/1M tokens
GPT-4 Turbo (OpenAI) — Coding Index 21.5, $15.0/1M tokens
Claude Fable 5.1 (Max, Default Fallback) (Anthropic) — Coding Index 81.6, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (Xhigh, Default Fallback) (Anthropic) — Coding Index 80.7, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (High, Default Fallback) (Anthropic) — Coding Index 79.1, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (High) (OpenAI) — Coding Index 77.1, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (Medium, Default Fallback) (Anthropic) — Coding Index 77.1, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Max) (OpenAI) — Coding Index 76.9, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Medium) (OpenAI) — Coding Index 76.7, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5 (Max, Opus 4.8 Fallback) (Anthropic) — Coding Index 76.5, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Xhigh) (OpenAI) — Coding Index 75.9, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Low) (OpenAI) — Coding Index 75.7, $20.0/1M tokens
Claude Fable 5.1 (Low, Default Fallback) (Anthropic) — Coding Index 75.2, $20.0/1M tokens
o1 (OpenAI) — Coding Index 39.7, $26.25/1M tokens
o1-preview (OpenAI) — Coding Index 34.0, $28.875/1M tokens
Claude 3 Opus (Anthropic) — Coding Index 19.5, $30.0/1M tokens
GPT-4 (OpenAI) — Coding Index 13.1, $37.5/1M tokens
Llama 3.1 Instruct 8B
Granite 4.2 3B
Qwen3.5 4B
Nemotron 3.5 Lightning
Ling-3.0-flash-VL
Qwen3.8-Flash-Next
Gemini 3.8 Flash
Muse Spark 1.3
Grok 4.6
GPT-5.6 Sol
Claude Fable 5.1
Humanity's Last Exam ↑
20
40
60
$0.1
$1
$10
1M 토큰당 가격
(USD · 로그 축) →
Llama 3.1 Instruct 8B (Meta) — Humanity's Last Exam 5.3, $0.028/1M tokens (클릭: 관련 논문)
Gemma 4 E4B (Non-reasoning) (Google) — Humanity's Last Exam 4.8, $0.04/1M tokens
Gemma 4 E4B (Reasoning) (Google) — Humanity's Last Exam 3.8, $0.04/1M tokens (클릭: 관련 논문)
Sarvam 30B (High) (Sarvam) — Humanity's Last Exam 7.5, $0.047/1M tokens
Granite 4.2 3B (IBM) — Humanity's Last Exam 6.6, $0.052/1M tokens
Mistral Small 3 (Mistral) — Humanity's Last Exam 3.8, $0.058/1M tokens
Qwen3.5 4B (Reasoning) (Alibaba) — Humanity's Last Exam 9.9, $0.06/1M tokens (클릭: 관련 논문)
Qwen3.5 4B (Non-reasoning) (Alibaba) — Humanity's Last Exam 8.0, $0.06/1M tokens
Nova Micro (Amazon) — Humanity's Last Exam 4.6, $0.061/1M tokens
Llama 3 Instruct 8B (Meta) — Humanity's Last Exam 5.1, $0.07/1M tokens
NVIDIA Nemotron Nano 9B V2 (Reasoning) (NVIDIA) — Humanity's Last Exam 4.9, $0.07/1M tokens
Sarvam 105B (High) (Sarvam) — Humanity's Last Exam 11.0, $0.074/1M tokens
Granite 3.3 8B (Non-reasoning) (IBM) — Humanity's Last Exam 4.2, $0.085/1M tokens
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) (NVIDIA) — Humanity's Last Exam 4.6, $0.086/1M tokens
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA) — Humanity's Last Exam 11.4, $0.088/1M tokens
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) (NVIDIA) — Humanity's Last Exam 4.6, $0.088/1M tokens
Qwen2.5 Turbo (Alibaba) — Humanity's Last Exam 4.1, $0.088/1M tokens
Nemotron 3.5 Lightning (NVIDIA) — Humanity's Last Exam 10.6, $0.095/1M tokens (클릭: 관련 논문)
gpt-oss-20b (High) (OpenAI) — Humanity's Last Exam 11.0, $0.098/1M tokens
Hy3-preview (Reasoning) (Tencent) — Humanity's Last Exam 27.8, $0.1/1M tokens
Hy3-preview (Non-reasoning) (Tencent) — Humanity's Last Exam 7.0, $0.1/1M tokens
Ministral 3 3B (Mistral) — Humanity's Last Exam 5.4, $0.1/1M tokens
Llama 2 Chat 7B (Meta) — Humanity's Last Exam 5.3, $0.1/1M tokens
Nova Lite (Amazon) — Humanity's Last Exam 4.3, $0.105/1M tokens
gpt-oss-20b (Low) (OpenAI) — Humanity's Last Exam 5.3, $0.106/1M tokens
Mistral Small 3.2 (Mistral) — Humanity's Last Exam 4.3, $0.106/1M tokens
Granite 4.2 8B (IBM) — Humanity's Last Exam 9.7, $0.107/1M tokens
Granite 4.0 H Small (IBM) — Humanity's Last Exam 3.8, $0.107/1M tokens
Ling 3.0 Flash (InclusionAI) — Humanity's Last Exam 23.7, $0.111/1M tokens
Ling-3.0-flash-Fin (InclusionAI) — Humanity's Last Exam 22.6, $0.111/1M tokens
Ling-3.0-flash-VL (InclusionAI) — Humanity's Last Exam 22.0, $0.111/1M tokens
DeepSeek V4 Flash 0420 (Non-reasoning) (DeepSeek) — Humanity's Last Exam 7.8, $0.117/1M tokens
Olmo 3 7B Instruct (Allen Institute for AI) — Humanity's Last Exam 5.8, $0.125/1M tokens
Apertus 8B Instruct (Swiss AI Initiative) — Humanity's Last Exam 5.0, $0.125/1M tokens
Mistral Small 3.1 (Mistral) — Humanity's Last Exam 4.3, $0.125/1M tokens
GPT-5 nano (High) (OpenAI) — Humanity's Last Exam 9.5, $0.138/1M tokens
GPT-5 nano (Medium) (OpenAI) — Humanity's Last Exam 8.7, $0.138/1M tokens
GPT-5 nano (Minimal) (OpenAI) — Humanity's Last Exam 4.0, $0.138/1M tokens
Step 3.5 Flash 2603 (StepFun) — Humanity's Last Exam 24.5, $0.15/1M tokens
MiMo-V2-Flash (Reasoning) (Xiaomi) — Humanity's Last Exam 22.8, $0.15/1M tokens
Step 3.5 Flash (StepFun) — Humanity's Last Exam 21.1, $0.15/1M tokens
Gemma 4 12B (Reasoning) (Google) — Humanity's Last Exam 15.7, $0.15/1M tokens
Gemma 4 12B (Non-reasoning) (Google) — Humanity's Last Exam 6.3, $0.15/1M tokens
Ministral 3 8B (Mistral) — Humanity's Last Exam 4.3, $0.15/1M tokens
Qwen3.5 9B (Reasoning) (Alibaba) — Humanity's Last Exam 14.9, $0.151/1M tokens
GLM-4.7-Flash (Reasoning) (Z AI) — Humanity's Last Exam 7.6, $0.153/1M tokens
GLM-4.7-Flash (Non-reasoning) (Z AI) — Humanity's Last Exam 5.0, $0.153/1M tokens
Mistral 7B Instruct (Mistral) — Humanity's Last Exam 4.5, $0.162/1M tokens
DeepSeek V4 Flash 0420 (Max) (DeepSeek) — Humanity's Last Exam 34.8, $0.168/1M tokens
DeepSeek V4 Flash 0420 (High) (DeepSeek) — Humanity's Last Exam 30.3, $0.168/1M tokens
Gemma 4 26B A4B (Reasoning) (Google) — Humanity's Last Exam 19.3, $0.168/1M tokens
MiMo-V2.6-Flash (Xiaomi) — Humanity's Last Exam 35.1, $0.175/1M tokens (클릭: 관련 논문)
MiMo-V2.5 (Xiaomi) — Humanity's Last Exam 27.2, $0.175/1M tokens
Solar Mini 4 (Upstage) — Humanity's Last Exam 25.8, $0.175/1M tokens
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) (Google) — Humanity's Last Exam 7.0, $0.175/1M tokens
Gemini 2.5 Flash-Lite (Reasoning) (Google) — Humanity's Last Exam 6.8, $0.175/1M tokens
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) (Google) — Humanity's Last Exam 5.1, $0.175/1M tokens
GPT-4.1 nano (OpenAI) — Humanity's Last Exam 3.8, $0.175/1M tokens
Gemini 2.5 Flash-Lite (Non-reasoning) (Google) — Humanity's Last Exam 3.7, $0.175/1M tokens
Qwen3.5 9B (Non-reasoning) (Alibaba) — Humanity's Last Exam 9.4, $0.19/1M tokens
Gemma 4 26B A4B (Non-reasoning) (Google) — Humanity's Last Exam 11.5, $0.198/1M tokens
Claude Haiku 5.5 (Max) (Anthropic) — Humanity's Last Exam 44.4, $0.2/1M tokens
Claude Haiku 5.5 (Xhigh) (Anthropic) — Humanity's Last Exam 42.7, $0.2/1M tokens
GPT-6 Luna (Max) (OpenAI) — Humanity's Last Exam 38.5, $0.2/1M tokens
Claude Haiku 5.5 (High) (Anthropic) — Humanity's Last Exam 37.3, $0.2/1M tokens
GPT-6 Luna (Xhigh) (OpenAI) — Humanity's Last Exam 34.3, $0.2/1M tokens
Claude Haiku 5.5 (Medium) (Anthropic) — Humanity's Last Exam 33.8, $0.2/1M tokens
GPT-6 Luna (High) (OpenAI) — Humanity's Last Exam 32.9, $0.2/1M tokens
GPT-6 Luna (Medium) (OpenAI) — Humanity's Last Exam 28.3, $0.2/1M tokens
Claude Haiku 5.5 (Low) (Anthropic) — Humanity's Last Exam 27.0, $0.2/1M tokens
GPT-6 Luna (Low) (OpenAI) — Humanity's Last Exam 20.3, $0.2/1M tokens
GPT-6 Luna (Non-reasoning) (OpenAI) — Humanity's Last Exam 8.6, $0.2/1M tokens
Ministral 3 14B (Mistral) — Humanity's Last Exam 4.6, $0.2/1M tokens
Phi-4 (Microsoft) — Humanity's Last Exam 3.8, $0.219/1M tokens
Gemma 4 31B (Non-reasoning) (Google) — Humanity's Last Exam 11.8, $0.224/1M tokens
Qwen3.8-Flash-Next (Alibaba) — Humanity's Last Exam 38.0, $0.23/1M tokens (클릭: 관련 논문)
GLM 5.3 Flash (Z AI) — Humanity's Last Exam 39.9, $0.237/1M tokens
Hy3 (Tencent) — Humanity's Last Exam 33.5, $0.241/1M tokens
Ring-flash-2.0 (InclusionAI) — Humanity's Last Exam 9.6, $0.247/1M tokens
Ling-flash-2.0 (InclusionAI) — Humanity's Last Exam 6.2, $0.247/1M tokens
gpt-oss-120b (Low) (OpenAI) — Humanity's Last Exam 5.9, $0.249/1M tokens
Jamba 1.5 Mini (AI21 Labs) — Humanity's Last Exam 5.1, $0.25/1M tokens
gpt-oss-120b (High) (OpenAI) — Humanity's Last Exam 19.6, $0.261/1M tokens
Solar Pro 3 (Upstage) — Humanity's Last Exam 10.3, $0.262/1M tokens
Mistral Small 4 (Reasoning) (Mistral) — Humanity's Last Exam 9.9, $0.262/1M tokens
GPT-4o mini (OpenAI) — Humanity's Last Exam 4.2, $0.262/1M tokens
Mistral Small 4 (Non-reasoning) (Mistral) — Humanity's Last Exam 3.8, $0.262/1M tokens
Grok 4 Fast (Reasoning) (SpaceXAI) — Humanity's Last Exam 19.1, $0.275/1M tokens
Qwen3.5 Omni Flash (Alibaba) — Humanity's Last Exam 7.6, $0.275/1M tokens
Grok 4 Fast (Non-reasoning) (SpaceXAI) — Humanity's Last Exam 4.5, $0.275/1M tokens
Qwen3 VL 32B (Reasoning) (Alibaba) — Humanity's Last Exam 10.1, $0.28/1M tokens
Qwen3 32B (Reasoning) (Alibaba) — Humanity's Last Exam 7.4, $0.28/1M tokens
Qwen3 VL 32B Instruct (Alibaba) — Humanity's Last Exam 6.8, $0.28/1M tokens
Qwen3 32B (Non-reasoning) (Alibaba) — Humanity's Last Exam 4.1, $0.28/1M tokens
Granite 4.2 30B (IBM) — Humanity's Last Exam 11.2, $0.282/1M tokens
Seed-OSS-36B-Instruct (ByteDance Seed) — Humanity's Last Exam 9.9, $0.3/1M tokens
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) (NVIDIA) — Humanity's Last Exam 4.3, $0.3/1M tokens
Qwen3 VL 8B Instruct (Alibaba) — Humanity's Last Exam 2.7, $0.31/1M tokens
Qwen3 8B (Non-reasoning) (Alibaba) — Humanity's Last Exam 1.9, $0.31/1M tokens
Llama 4 Scout (Meta) — Humanity's Last Exam 3.8, $0.313/1M tokens
DeepSeek V3.2 (Reasoning) (DeepSeek) — Humanity's Last Exam 24.6, $0.315/1M tokens
DeepSeek V3.2 Exp (Reasoning) (DeepSeek) — Humanity's Last Exam 14.9, $0.315/1M tokens
DeepSeek V3.2 (Non-reasoning) (DeepSeek) — Humanity's Last Exam 11.2, $0.315/1M tokens
DeepSeek V3.2 Exp (Non-reasoning) (DeepSeek) — Humanity's Last Exam 9.0, $0.315/1M tokens
Celeris-1 (Celeris) — Humanity's Last Exam 6.8, $0.325/1M tokens
Llama 3.2 Instruct 11B (Vision) (Meta) — Humanity's Last Exam 5.5, $0.345/1M tokens
Grok 3 mini Reasoning (High) (SpaceXAI) — Humanity's Last Exam 11.0, $0.35/1M tokens
Qwen3 30B A3B 2507 Instruct (Alibaba) — Humanity's Last Exam 6.9, $0.35/1M tokens
Qwen3 VL 30B A3B Instruct (Alibaba) — Humanity's Last Exam 6.3, $0.35/1M tokens
Qwen3 30B A3B (Non-reasoning) (Alibaba) — Humanity's Last Exam 4.6, $0.35/1M tokens
Reka Flash 3 (Reka AI) — Humanity's Last Exam 4.4, $0.35/1M tokens
GLM-4.5-Air (Z AI) — Humanity's Last Exam 7.0, $0.372/1M tokens
Mercury 2 (Inception) — Humanity's Last Exam 17.1, $0.375/1M tokens
Mercury 2.5 (Inception) — Humanity's Last Exam 11.8, $0.375/1M tokens
Trinity Large Thinking (Arcee AI) — Humanity's Last Exam 15.8, $0.388/1M tokens
Qwen3 235B A22B 2507 Instruct (Alibaba) — Humanity's Last Exam 11.1, $0.403/1M tokens
Llama 4 Maverick (Meta) — Humanity's Last Exam 4.9, $0.405/1M tokens
DeepSeek V3 0324 (DeepSeek) — Humanity's Last Exam 4.7, $0.405/1M tokens
Qwen3 Next 80B A3B (Reasoning) (Alibaba) — Humanity's Last Exam 12.6, $0.412/1M tokens
Qwen3 Next 80B A3B Instruct (Alibaba) — Humanity's Last Exam 7.6, $0.412/1M tokens
Qwen3 Omni 30B A3B (Reasoning) (Alibaba) — Humanity's Last Exam 7.5, $0.43/1M tokens
Qwen3 Omni 30B A3B Instruct (Alibaba) — Humanity's Last Exam 4.6, $0.43/1M tokens
Step 3.7 Flash (StepFun) — Humanity's Last Exam 21.4, $0.438/1M tokens
GPT-5.6 Luna (Max) (OpenAI) — Humanity's Last Exam 39.5, $0.45/1M tokens
Ling 3.1 Flash (InclusionAI) — Humanity's Last Exam 39.4, $0.45/1M tokens
GPT-5.6 Luna (Xhigh) (OpenAI) — Humanity's Last Exam 37.0, $0.45/1M tokens
GPT-5.6 Luna (High) (OpenAI) — Humanity's Last Exam 33.4, $0.45/1M tokens
GPT-5.6 Luna (Medium) (OpenAI) — Humanity's Last Exam 25.8, $0.45/1M tokens
Nemotron 3 Super 120B A12B (Reasoning) (NVIDIA) — Humanity's Last Exam 20.8, $0.45/1M tokens
GPT-5.6 Luna (Low) (OpenAI) — Humanity's Last Exam 19.8, $0.45/1M tokens
GLM-4.6V (Reasoning) (Z AI) — Humanity's Last Exam 9.6, $0.45/1M tokens
GPT-5.6 Luna (Non-reasoning) (OpenAI) — Humanity's Last Exam 7.2, $0.45/1M tokens
Nemotron 3 Nano Omni 30B A3B Reasoning (NVIDIA) — Humanity's Last Exam 4.8, $0.45/1M tokens
GLM-4.6V (Non-reasoning) (Z AI) — Humanity's Last Exam 3.7, $0.45/1M tokens
DeepSeek V3.1 Terminus (Non-reasoning) (DeepSeek) — Humanity's Last Exam 8.7, $0.453/1M tokens
GPT-5.4 nano (Xhigh) (OpenAI) — Humanity's Last Exam 28.3, $0.463/1M tokens
GPT-5.4 nano (Medium) (OpenAI) — Humanity's Last Exam 15.9, $0.463/1M tokens
GPT-5.4 nano (Non-reasoning) (OpenAI) — Humanity's Last Exam 4.1, $0.463/1M tokens
DeepSeek V3 (Dec '24) (DeepSeek) — Humanity's Last Exam 2.9, $0.463/1M tokens
Qwen2.5 Instruct 72B (Alibaba) — Humanity's Last Exam 3.6, $0.48/1M tokens
ERNIE 4.5 300B A47B (Baidu) — Humanity's Last Exam 3.3, $0.485/1M tokens
Claude 3 Haiku (Anthropic) — Humanity's Last Exam 4.1, $0.5/1M tokens
Mixtral 8x7B Instruct (Mistral) — Humanity's Last Exam 4.7, $0.512/1M tokens
DeepSeek V4.1 Flash (Max) (DeepSeek) — Humanity's Last Exam 39.2, $0.525/1M tokens
MiniMax-M3 (MiniMax) — Humanity's Last Exam 39.0, $0.525/1M tokens
LongCat 2.0 (LongCat) — Humanity's Last Exam 33.7, $0.525/1M tokens
Inkling Small (Thinking Machines) — Humanity's Last Exam 33.3, $0.525/1M tokens
MiniMax-M2.7 (MiniMax) — Humanity's Last Exam 29.6, $0.525/1M tokens
Solar Pro 4 (Upstage) — Humanity's Last Exam 29.2, $0.525/1M tokens
MiniMax-M2.1 (MiniMax) — Humanity's Last Exam 23.2, $0.525/1M tokens
MiniMax-M2.5 (MiniMax) — Humanity's Last Exam 20.5, $0.525/1M tokens
KAT Coder Pro V2 (KwaiKAT) — Humanity's Last Exam 16.1, $0.525/1M tokens
MiniMax-M2 (MiniMax) — Humanity's Last Exam 13.7, $0.525/1M tokens
DeepSeek V4.1 Flash (Non-reasoning) (DeepSeek) — Humanity's Last Exam 10.8, $0.525/1M tokens
MiMo-V2.6-Pro (Xiaomi) — Humanity's Last Exam 49.4, $0.544/1M tokens (클릭: 관련 논문)
DeepSeek V4 Pro 0424 (Max) (DeepSeek) — Humanity's Last Exam 37.5, $0.544/1M tokens
MiMo-V2.5-Pro (Reasoning) (Xiaomi) — Humanity's Last Exam 35.7, $0.544/1M tokens
DeepSeek V4 Pro 0424 (High) (DeepSeek) — Humanity's Last Exam 35.2, $0.544/1M tokens
MiMo-V2.5-Pro (Non-reasoning) (Xiaomi) — Humanity's Last Exam 14.8, $0.544/1M tokens
DeepSeek V4 Pro 0424 (Non-reasoning) (DeepSeek) — Humanity's Last Exam 8.2, $0.544/1M tokens
Llama 3.1 Instruct 70B (Meta) — Humanity's Last Exam 4.5, $0.56/1M tokens
Gemini 3.1 Flash-Lite (Google) — Humanity's Last Exam 17.2, $0.563/1M tokens
Qwen3 Coder Next (Alibaba) — Humanity's Last Exam 10.1, $0.563/1M tokens
Muse Glimmer (High) (Meta) — Humanity's Last Exam 22.0, $0.581/1M tokens
Qwen3 14B (Non-reasoning) (Alibaba) — Humanity's Last Exam 4.1, $0.612/1M tokens
DeepSeek V4 Flash 0731 (Max) (DeepSeek) — Humanity's Last Exam 38.6, $0.66/1M tokens
DeepSeek V4 Flash Vision (Max) (DeepSeek) — Humanity's Last Exam 34.5, $0.66/1M tokens
Qwen3 8B (Reasoning) (Alibaba) — Humanity's Last Exam 3.9, $0.66/1M tokens
Qwen3 VL 8B (Reasoning) (Alibaba) — Humanity's Last Exam 3.8, $0.66/1M tokens
GPT-5 mini (High) (OpenAI) — Humanity's Last Exam 21.5, $0.688/1M tokens
Qwen3.5 35B A3B (Reasoning) (Alibaba) — Humanity's Last Exam 21.0, $0.688/1M tokens
GPT-5.1 Codex mini (High) (OpenAI) — Humanity's Last Exam 18.5, $0.688/1M tokens
GPT-5 mini (Medium) (OpenAI) — Humanity's Last Exam 15.9, $0.688/1M tokens
Qwen3.5 35B A3B (Non-reasoning) (Alibaba) — Humanity's Last Exam 13.4, $0.688/1M tokens
GPT-5 mini (Minimal) (OpenAI) — Humanity's Last Exam 5.1, $0.688/1M tokens
Qwen3.7 Plus (Alibaba) — Humanity's Last Exam 35.6, $0.7/1M tokens
Qwen3 VL 235B A22B Instruct (Alibaba) — Humanity's Last Exam 6.6, $0.7/1M tokens
GPT-4.1 mini (OpenAI) — Humanity's Last Exam 5.0, $0.7/1M tokens
Hermes 3 - Llama-3.1 70B (Nous Research) — Humanity's Last Exam 4.0, $0.7/1M tokens
Llama 3.3 Instruct 70B (Meta) — Humanity's Last Exam 3.6, $0.712/1M tokens
QwQ 32B (Alibaba) — Humanity's Last Exam 7.3, $0.745/1M tokens
Qwen3 235B A22B 2507 (Reasoning) (Alibaba) — Humanity's Last Exam 15.9, $0.747/1M tokens
Qwen3 30B A3B 2507 (Reasoning) (Alibaba) — Humanity's Last Exam 10.3, $0.75/1M tokens
Qwen3 VL 30B A3B (Reasoning) (Alibaba) — Humanity's Last Exam 8.9, $0.75/1M tokens
Magistral Small 1.2 (Mistral) — Humanity's Last Exam 6.4, $0.75/1M tokens
Qwen3 30B A3B (Reasoning) (Alibaba) — Humanity's Last Exam 6.2, $0.75/1M tokens
Mistral Large 3 (Mistral) — Humanity's Last Exam 4.2, $0.75/1M tokens
DeepSeek R1 Distill Llama 70B (DeepSeek) — Humanity's Last Exam 5.1, $0.8/1M tokens
Mistral Medium 3 (Mistral) — Humanity's Last Exam 4.1, $0.8/1M tokens
Qwen3.5 27B (Reasoning) (Alibaba) — Humanity's Last Exam 23.9, $0.825/1M tokens
Qwen3.5 27B (Non-reasoning) (Alibaba) — Humanity's Last Exam 13.9, $0.825/1M tokens
DeepSeek V3.1 (Non-reasoning) (DeepSeek) — Humanity's Last Exam 6.7, $0.84/1M tokens
Qwen3.6 35B A3B (Reasoning) (Alibaba) — Humanity's Last Exam 22.2, $0.844/1M tokens
Qwen3.6 35B A3B (Non-reasoning) (Alibaba) — Humanity's Last Exam 13.9, $0.844/1M tokens
Ring-2.6-1T (InclusionAI) — Humanity's Last Exam 21.6, $0.85/1M tokens
Gemini 3.5 Flash-Lite (Google) — Humanity's Last Exam 18.8, $0.85/1M tokens
Gemini 2.5 Flash (Reasoning) (Google) — Humanity's Last Exam 12.1, $0.85/1M tokens
Nova 2.0 Lite (High) (Amazon) — Humanity's Last Exam 11.6, $0.85/1M tokens
Nova 2.0 Lite (Medium) (Amazon) — Humanity's Last Exam 9.0, $0.85/1M tokens
Ling-2.6-1T (InclusionAI) — Humanity's Last Exam 8.7, $0.85/1M tokens
Nova 2.0 Omni (Medium) (Amazon) — Humanity's Last Exam 7.0, $0.85/1M tokens
Gemini 2.5 Flash (Non-reasoning) (Google) — Humanity's Last Exam 4.7, $0.85/1M tokens
Nova 2.0 Lite (Low) (Amazon) — Humanity's Last Exam 4.0, $0.85/1M tokens
Nova 2.0 Omni (Non-reasoning) (Amazon) — Humanity's Last Exam 3.8, $0.85/1M tokens
Nova 2.0 Lite (Non-reasoning) (Amazon) — Humanity's Last Exam 2.9, $0.85/1M tokens
DeepSeek V3.1 (Reasoning) (DeepSeek) — Humanity's Last Exam 14.3, $0.855/1M tokens
Quasar 438B (Max, Based on GLM-5.2) (Multiverse Computing) — Humanity's Last Exam 18.7, $0.9/1M tokens
GLM-4.5V (Reasoning) (Z AI) — Humanity's Last Exam 6.3, $0.9/1M tokens
Qwen3 Coder 30B A3B Instruct (Alibaba) — Humanity's Last Exam 3.8, $0.9/1M tokens
GLM-4.5V (Non-reasoning) (Z AI) — Humanity's Last Exam 3.5, $0.9/1M tokens
GLM-4.6 (Reasoning) (Z AI) — Humanity's Last Exam 14.5, $0.963/1M tokens
MiniMax M1 80k (MiniMax) — Humanity's Last Exam 8.9, $0.963/1M tokens
Apodex 1.1 (Apodex) — Humanity's Last Exam 34.1, $0.975/1M tokens
GLM-4.6 (Non-reasoning) (Z AI) — Humanity's Last Exam 5.5, $0.981/1M tokens
GLM-4.7 (Reasoning) (Z AI) — Humanity's Last Exam 27.4, $1.0/1M tokens
GLM-4.7 (Non-reasoning) (Z AI) — Humanity's Last Exam 6.4, $1.0/1M tokens
Kimi K2 (Kimi) — Humanity's Last Exam 7.4, $1.002/1M tokens
Nemotron 3 Ultra 550B A55B (Reasoning) (NVIDIA) — Humanity's Last Exam 28.4, $1.075/1M tokens
Kimi K2 Thinking (Kimi) — Humanity's Last Exam 23.8, $1.075/1M tokens
Kimi K2 0905 (Kimi) — Humanity's Last Exam 6.4, $1.075/1M tokens
Qwen3.5 122B A10B (Reasoning) (Alibaba) — Humanity's Last Exam 25.2, $1.1/1M tokens
Qwen3.5 122B A10B (Non-reasoning) (Alibaba) — Humanity's Last Exam 15.9, $1.1/1M tokens
Gemini 3 Flash Preview (Reasoning) (Google) — Humanity's Last Exam 36.6, $1.125/1M tokens
Qwen3.8 27B (Xhigh) (Alibaba) — Humanity's Last Exam 33.9, $1.125/1M tokens
Qwen3.6 Plus (Alibaba) — Humanity's Last Exam 27.8, $1.125/1M tokens
Gemini 3 Flash Preview (Non-reasoning) (Google) — Humanity's Last Exam 15.0, $1.125/1M tokens
Qwen3.8 27B (Medium) (Alibaba) — Humanity's Last Exam 14.1, $1.125/1M tokens
Qwen3.8 27B (Low) (Alibaba) — Humanity's Last Exam 14.0, $1.125/1M tokens
Qwen3.8 27B (Non-reasoning) (Alibaba) — Humanity's Last Exam 12.1, $1.125/1M tokens
Kimi K2.5 (Reasoning) (Kimi) — Humanity's Last Exam 30.7, $1.137/1M tokens
Llama 3 Instruct 70B (Meta) — Humanity's Last Exam 4.5, $1.175/1M tokens
Kimi K2.5 (Non-reasoning) (Kimi) — Humanity's Last Exam 13.2, $1.2/1M tokens
Qwen3 235B A22B (Non-reasoning) (Alibaba) — Humanity's Last Exam 4.2, $1.225/1M tokens
Grok Build 0.1 0616 (SpaceXAI) — Humanity's Last Exam 38.3, $1.25/1M tokens
Cogito v2.1 (Reasoning) (Deep Cogito) — Humanity's Last Exam 12.0, $1.25/1M tokens
Qwen3 VL 235B A22B (Reasoning) (Alibaba) — Humanity's Last Exam 11.9, $1.3/1M tokens
Qwen3 14B (Reasoning) (Alibaba) — Humanity's Last Exam 4.5, $1.313/1M tokens
Apertus 70B Instruct (Swiss AI Initiative) — Humanity's Last Exam 5.5, $1.345/1M tokens
Qwen3.5 397B A17B (Reasoning) (Alibaba) — Humanity's Last Exam 29.0, $1.35/1M tokens
Qwen3.6 27B (Reasoning) (Alibaba) — Humanity's Last Exam 23.1, $1.35/1M tokens
Qwen3.5 397B A17B (Non-reasoning) (Alibaba) — Humanity's Last Exam 19.8, $1.35/1M tokens
Qwen3.6 27B (Non-reasoning) (Alibaba) — Humanity's Last Exam 15.1, $1.35/1M tokens
Nova Pro (Amazon) — Humanity's Last Exam 3.2, $1.4/1M tokens
Step 5 Preview (StepFun) — Humanity's Last Exam 46.5, $1.425/1M tokens
Gemini 3.7 Flash (High) (Google) — Humanity's Last Exam 47.9, $1.5/1M tokens (클릭: 관련 논문)
Gemini 3.8 Flash (High) (Google) — Humanity's Last Exam 47.8, $1.5/1M tokens (클릭: 관련 논문)
Gemini 3.8 Flash (Medium) (Google) — Humanity's Last Exam 42.1, $1.5/1M tokens
Gemini 3.6 Flash (High) (Google) — Humanity's Last Exam 40.8, $1.5/1M tokens
Gemini 3.7 Flash (Medium) (Google) — Humanity's Last Exam 39.0, $1.5/1M tokens
Gemini 3.8 Flash (Low) (Google) — Humanity's Last Exam 37.1, $1.5/1M tokens
Gemini 3.7 Flash (Low) (Google) — Humanity's Last Exam 35.1, $1.5/1M tokens
Qwen3.5 Omni Plus (Alibaba) — Humanity's Last Exam 14.9, $1.5/1M tokens
Hermes 4 - Llama-3.1 405B (Reasoning) (Nous Research) — Humanity's Last Exam 10.9, $1.5/1M tokens
Hermes 4 - Llama-3.1 405B (Non-reasoning) (Nous Research) — Humanity's Last Exam 4.2, $1.5/1M tokens
GLM-5 (Reasoning) (Z AI) — Humanity's Last Exam 29.3, $1.55/1M tokens
GLM-5 (Non-reasoning) (Z AI) — Humanity's Last Exam 7.6, $1.55/1M tokens
Grok 4.3 (High) (SpaceXAI) — Humanity's Last Exam 37.2, $1.563/1M tokens
Grok 4.20 0309 v2 (Reasoning) (SpaceXAI) — Humanity's Last Exam 34.5, $1.563/1M tokens
Grok 4.3 (Medium) (SpaceXAI) — Humanity's Last Exam 30.0, $1.563/1M tokens
Grok 4.20 0309 v2 (Non-reasoning) (SpaceXAI) — Humanity's Last Exam 27.9, $1.563/1M tokens
Grok 4.3 (Low) (SpaceXAI) — Humanity's Last Exam 18.4, $1.563/1M tokens
Grok 4.3 (Non-reasoning) (SpaceXAI) — Humanity's Last Exam 6.8, $1.563/1M tokens
GPT-5.4 mini (Xhigh) (OpenAI) — Humanity's Last Exam 28.1, $1.688/1M tokens
GPT-5.4 mini (Medium) (OpenAI) — Humanity's Last Exam 18.6, $1.688/1M tokens
GPT-5.4 mini (Non-reasoning) (OpenAI) — Humanity's Last Exam 5.9, $1.688/1M tokens
Kimi K2.6 (Reasoning) (Kimi) — Humanity's Last Exam 37.5, $1.712/1M tokens
Kimi K2.7 Code (Kimi) — Humanity's Last Exam 35.0, $1.712/1M tokens
Kimi K2.6 (Non-reasoning) (Kimi) — Humanity's Last Exam 19.6, $1.712/1M tokens
Inkling (Xhigh) (Thinking Machines) — Humanity's Last Exam 31.9, $1.762/1M tokens
DeepSeek R1 0528 (May '25) (DeepSeek) — Humanity's Last Exam 15.8, $1.763/1M tokens
DeepSeek V3.1 Terminus (Reasoning) (DeepSeek) — Humanity's Last Exam 16.4, $1.914/1M tokens
o4-mini (High) (OpenAI) — Humanity's Last Exam 16.5, $1.925/1M tokens
o3-mini (High) (OpenAI) — Humanity's Last Exam 12.0, $1.925/1M tokens
o3-mini (OpenAI) — Humanity's Last Exam 7.9, $1.925/1M tokens
DeepSeek V4 Pro 0813 (Max) (DeepSeek) — Humanity's Last Exam 41.0, $1.98/1M tokens
DeepSeek V4 Pro 0813 (Non-reasoning) (DeepSeek) — Humanity's Last Exam 10.6, $1.98/1M tokens
GLM-5.1 (Reasoning) (Z AI) — Humanity's Last Exam 30.1, $1.981/1M tokens
Muse Spark 1.3 (Max) (Meta) — Humanity's Last Exam 48.7, $2.0/1M tokens (클릭: 관련 논문)
Muse Spark 1.3 (Xhigh) (Meta) — Humanity's Last Exam 47.5, $2.0/1M tokens (클릭: 관련 논문)
Muse Spark 1.1 (Xhigh) (Meta) — Humanity's Last Exam 46.2, $2.0/1M tokens
Muse Spark 1.2 (Xhigh) (Meta) — Humanity's Last Exam 45.5, $2.0/1M tokens
Claude 4.5 Haiku (Reasoning) (Anthropic) — Humanity's Last Exam 10.4, $2.0/1M tokens
Claude 4.5 Haiku (Non-reasoning) (Anthropic) — Humanity's Last Exam 4.2, $2.0/1M tokens
Mistral Large 4 Preview (Mistral) — Humanity's Last Exam 35.0, $2.065/1M tokens
GLM-5.1 (Non-reasoning) (Z AI) — Humanity's Last Exam 27.9, $2.135/1M tokens
GLM-5.3 (Max) (Z AI) — Humanity's Last Exam 42.3, $2.15/1M tokens
GLM-5.2 (Max) (Z AI) — Humanity's Last Exam 41.1, $2.15/1M tokens
GLM-5.3 (Low) (Z AI) — Humanity's Last Exam 36.6, $2.15/1M tokens
GLM-5.2 (Non-reasoning) (Z AI) — Humanity's Last Exam 9.8, $2.15/1M tokens
Qwen3 Max Thinking (Preview) (Alibaba) — Humanity's Last Exam 12.7, $2.4/1M tokens
Qwen3 Max (Alibaba) — Humanity's Last Exam 11.9, $2.4/1M tokens
Qwen3 Max (Preview) (Alibaba) — Humanity's Last Exam 10.1, $2.4/1M tokens
DeepSeek R1 (Jan '25) (DeepSeek) — Humanity's Last Exam 8.5, $2.5/1M tokens
Qwen3 235B A22B (Reasoning) (Alibaba) — Humanity's Last Exam 11.0, $2.625/1M tokens
Qwen3.6 Max Preview (Alibaba) — Humanity's Last Exam 30.8, $2.925/1M tokens
Grok 4.6 (Xhigh) (SpaceXAI) — Humanity's Last Exam 44.1, $3.0/1M tokens (클릭: 관련 논문)
Grok 4.7 (Xhigh) (SpaceXAI) — Humanity's Last Exam 43.1, $3.0/1M tokens
Qwen3.8 Max (0902) (Alibaba) — Humanity's Last Exam 43.1, $3.0/1M tokens (클릭: 관련 논문)
Qwen3.8 Max (Alibaba) — Humanity's Last Exam 43.0, $3.0/1M tokens
Grok 4.6 (High) (SpaceXAI) — Humanity's Last Exam 42.9, $3.0/1M tokens (클릭: 관련 논문)
Grok 4.5 (High) (SpaceXAI) — Humanity's Last Exam 42.7, $3.0/1M tokens
Qwen3.8 2.4T A95B (Alibaba) — Humanity's Last Exam 42.4, $3.0/1M tokens
Grok 4.7 (High) (SpaceXAI) — Humanity's Last Exam 42.3, $3.0/1M tokens
Grok 4.6 (Medium) (SpaceXAI) — Humanity's Last Exam 42.1, $3.0/1M tokens
Grok 4.7 (Low) (SpaceXAI) — Humanity's Last Exam 39.2, $3.0/1M tokens
Grok 4.20 0309 (Reasoning) (SpaceXAI) — Humanity's Last Exam 32.4, $3.0/1M tokens
Grok 4.6 (Low) (SpaceXAI) — Humanity's Last Exam 27.6, $3.0/1M tokens
Grok 4.20 0309 (Non-reasoning) (SpaceXAI) — Humanity's Last Exam 24.5, $3.0/1M tokens
Mistral Medium 3.5 (Mistral) — Humanity's Last Exam 13.8, $3.0/1M tokens
Qwen3 Coder 480B A35B Instruct (Alibaba) — Humanity's Last Exam 4.5, $3.0/1M tokens
Mistral Large 2 (Jul '24) (Mistral) — Humanity's Last Exam 2.9, $3.0/1M tokens
Gemini 3.5 Flash (High) (Google) — Humanity's Last Exam 42.7, $3.375/1M tokens
Gemini 3.5 Flash (Medium) (Google) — Humanity's Last Exam 41.3, $3.375/1M tokens
Gemini 3.5 Flash (Minimal) (Google) — Humanity's Last Exam 24.1, $3.375/1M tokens
GPT-5.1 (High) (OpenAI) — Humanity's Last Exam 28.5, $3.438/1M tokens
GPT-5 (High) (OpenAI) — Humanity's Last Exam 28.5, $3.438/1M tokens
GPT-5 Codex (High) (OpenAI) — Humanity's Last Exam 27.8, $3.438/1M tokens
GPT-5.1 Codex (High) (OpenAI) — Humanity's Last Exam 25.7, $3.438/1M tokens
GPT-5 (Medium) (OpenAI) — Humanity's Last Exam 25.4, $3.438/1M tokens
Gemini 2.5 Pro (Google) — Humanity's Last Exam 22.5, $3.438/1M tokens
Gemini 2.5 Pro Preview (May' 25) (Google) — Humanity's Last Exam 19.9, $3.438/1M tokens
GPT-5 (Low) (OpenAI) — Humanity's Last Exam 19.6, $3.438/1M tokens
Nova 2.0 Pro Preview (Medium) (Amazon) — Humanity's Last Exam 9.4, $3.438/1M tokens
GPT-5 (Minimal) (OpenAI) — Humanity's Last Exam 6.0, $3.438/1M tokens
GPT-5.1 (Non-reasoning) (OpenAI) — Humanity's Last Exam 5.3, $3.438/1M tokens
Nova 2.0 Pro Preview (Low) (Amazon) — Humanity's Last Exam 5.2, $3.438/1M tokens
Nova 2.0 Pro Preview (Non-reasoning) (Amazon) — Humanity's Last Exam 3.9, $3.438/1M tokens
o3 (OpenAI) — Humanity's Last Exam 20.1, $3.5/1M tokens
GPT-4.1 (OpenAI) — Humanity's Last Exam 4.2, $3.5/1M tokens
Jamba 1.5 Large (AI21 Labs) — Humanity's Last Exam 4.1, $3.5/1M tokens
Qwen3.7 Max (Alibaba) — Humanity's Last Exam 40.5, $3.75/1M tokens
Gemini 4 Argon (High) (Google) — Humanity's Last Exam 57.1, $4.0/1M tokens (클릭: 관련 논문)
Claude Sonnet 5.5 (Max, Default Fallback) (Anthropic) — Humanity's Last Exam 55.0, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (Max) (OpenAI) — Humanity's Last Exam 52.9, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (Xhigh) (OpenAI) — Humanity's Last Exam 52.6, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (High) (OpenAI) — Humanity's Last Exam 51.4, $4.0/1M tokens (클릭: 관련 논문)
Claude Sonnet 5.5 (Xhigh, Default Fallback) (Anthropic) — Humanity's Last Exam 50.0, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (Medium) (OpenAI) — Humanity's Last Exam 49.9, $4.0/1M tokens (클릭: 관련 논문)
GPT-6 Sol (Max) (OpenAI) — Humanity's Last Exam 47.9, $4.0/1M tokens (클릭: 관련 논문)
GPT-6.1 Sol (Low) (OpenAI) — Humanity's Last Exam 47.4, $4.0/1M tokens
GPT-6 Sol (Xhigh) (OpenAI) — Humanity's Last Exam 46.3, $4.0/1M tokens
Claude Sonnet 5.5 (High, Default Fallback) (Anthropic) — Humanity's Last Exam 45.8, $4.0/1M tokens
GPT-6 Sol (High) (OpenAI) — Humanity's Last Exam 44.1, $4.0/1M tokens
Claude Sonnet 5 (Max) (Anthropic) — Humanity's Last Exam 41.3, $4.0/1M tokens
GPT-6 Sol (Medium) (OpenAI) — Humanity's Last Exam 41.0, $4.0/1M tokens
Claude Sonnet 5.5 (Medium, Default Fallback) (Anthropic) — Humanity's Last Exam 39.8, $4.0/1M tokens
Claude Sonnet 5 (Xhigh) (Anthropic) — Humanity's Last Exam 39.0, $4.0/1M tokens
Claude Sonnet 5.5 (Low, Default Fallback) (Anthropic) — Humanity's Last Exam 36.2, $4.0/1M tokens
Claude Sonnet 5 (High) (Anthropic) — Humanity's Last Exam 35.7, $4.0/1M tokens
GPT-6 Sol (Low) (OpenAI) — Humanity's Last Exam 34.9, $4.0/1M tokens
Claude Sonnet 5 (Medium) (Anthropic) — Humanity's Last Exam 30.0, $4.0/1M tokens
Claude Sonnet 5 (Low) (Anthropic) — Humanity's Last Exam 21.9, $4.0/1M tokens
Claude Sonnet 5 (Non-reasoning, High) (Anthropic) — Humanity's Last Exam 19.0, $4.0/1M tokens
GPT-6 Sol (Non-reasoning) (OpenAI) — Humanity's Last Exam 18.4, $4.0/1M tokens
Command A (Cohere) — Humanity's Last Exam 4.0, $4.375/1M tokens
GPT-4o (Nov '24) (OpenAI) — Humanity's Last Exam 2.4, $4.375/1M tokens
GPT-4o (Aug '24) (OpenAI) — Humanity's Last Exam 2.3, $4.375/1M tokens
Gemini 3.1 Pro Preview (Google) — Humanity's Last Exam 47.0, $4.5/1M tokens
GPT-5.6 Terra (Max) (OpenAI) — Humanity's Last Exam 42.9, $4.5/1M tokens (클릭: 관련 논문)
GPT-5.6 Terra (Xhigh) (OpenAI) — Humanity's Last Exam 41.9, $4.5/1M tokens
Gemini 3 Pro Preview (High) (Google) — Humanity's Last Exam 39.7, $4.5/1M tokens
GPT-5.6 Terra (High) (OpenAI) — Humanity's Last Exam 38.5, $4.5/1M tokens
GPT-5.6 Terra (Medium) (OpenAI) — Humanity's Last Exam 33.3, $4.5/1M tokens
Gemini 3 Pro Preview (Low) (Google) — Humanity's Last Exam 29.5, $4.5/1M tokens
GPT-5.6 Terra (Low) (OpenAI) — Humanity's Last Exam 29.2, $4.5/1M tokens
GPT-5.6 Terra (Non-reasoning) (OpenAI) — Humanity's Last Exam 11.4, $4.5/1M tokens
GPT-5.3 Codex (Xhigh) (OpenAI) — Humanity's Last Exam 42.5, $4.813/1M tokens
GPT-5.2 (Xhigh) (OpenAI) — Humanity's Last Exam 37.7, $4.813/1M tokens
GPT-5.2 Codex (Xhigh) (OpenAI) — Humanity's Last Exam 35.7, $4.813/1M tokens
GPT-5.2 (Medium) (OpenAI) — Humanity's Last Exam 26.7, $4.813/1M tokens
GPT-5.2 (Non-reasoning) (OpenAI) — Humanity's Last Exam 8.0, $4.813/1M tokens
GPT-5.4 (Xhigh) (OpenAI) — Humanity's Last Exam 43.7, $5.625/1M tokens
GPT-5.4 (Low) (OpenAI) — Humanity's Last Exam 30.8, $5.625/1M tokens
GPT-5.4 (Non-reasoning) (OpenAI) — Humanity's Last Exam 11.3, $5.625/1M tokens
Kimi K3 (Max) (Kimi) — Humanity's Last Exam 46.9, $6.0/1M tokens (클릭: 관련 논문)
Claude Sonnet 4.6 (Max) (Anthropic) — Humanity's Last Exam 33.6, $6.0/1M tokens
Grok 4 (SpaceXAI) — Humanity's Last Exam 26.7, $6.0/1M tokens
Kimi K3 (Low) (Kimi) — Humanity's Last Exam 25.0, $6.0/1M tokens
Claude 4.5 Sonnet (Reasoning) (Anthropic) — Humanity's Last Exam 17.8, $6.0/1M tokens
Claude Sonnet 4.6 (Non-reasoning, High) (Anthropic) — Humanity's Last Exam 13.3, $6.0/1M tokens
Claude Sonnet 4.6 (Non-reasoning, Low) (Anthropic) — Humanity's Last Exam 11.2, $6.0/1M tokens
Claude 4.5 Sonnet (Non-reasoning) (Anthropic) — Humanity's Last Exam 7.2, $6.0/1M tokens
Claude 3.7 Sonnet (Non-reasoning) (Anthropic) — Humanity's Last Exam 4.2, $6.0/1M tokens
Claude 3.5 Sonnet (Oct '24) (Anthropic) — Humanity's Last Exam 3.7, $6.0/1M tokens
Mistral Large (Feb '24) (Mistral) — Humanity's Last Exam 3.5, $6.0/1M tokens
Claude 3.5 Sonnet (June '24) (Anthropic) — Humanity's Last Exam 3.2, $6.0/1M tokens
GPT-4o (May '24) (OpenAI) — Humanity's Last Exam 1.8, $7.5/1M tokens
Claude Opus 5.5 (Max, Default Fallback) (Anthropic) — Humanity's Last Exam 61.4, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (Xhigh, Default Fallback) (Anthropic) — Humanity's Last Exam 57.5, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (High, Default Fallback) (Anthropic) — Humanity's Last Exam 55.6, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (Medium, Default Fallback) (Anthropic) — Humanity's Last Exam 54.7, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Max) (OpenAI) — Humanity's Last Exam 49.5, $8.0/1M tokens (클릭: 관련 논문)
Claude Opus 5.5 (Low, Default Fallback) (Anthropic) — Humanity's Last Exam 48.3, $8.0/1M tokens
GPT-5.6 Sol (Xhigh) (OpenAI) — Humanity's Last Exam 47.3, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (High) (OpenAI) — Humanity's Last Exam 46.0, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Medium) (OpenAI) — Humanity's Last Exam 42.2, $8.0/1M tokens (클릭: 관련 논문)
GPT-5.6 Sol (Low) (OpenAI) — Humanity's Last Exam 39.4, $8.0/1M tokens
GPT-5.6 Sol (Non-reasoning) (OpenAI) — Humanity's Last Exam 16.7, $8.0/1M tokens
Grok 3 (SpaceXAI) — Humanity's Last Exam 4.1, $8.0/1M tokens
Claude Opus 5 (Max) (Anthropic) — Humanity's Last Exam 54.9, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (Xhigh) (Anthropic) — Humanity's Last Exam 54.4, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (High) (Anthropic) — Humanity's Last Exam 52.8, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 5 (Medium) (Anthropic) — Humanity's Last Exam 51.3, $10.0/1M tokens (클릭: 관련 논문)
Claude Opus 4.8 (Max) (Anthropic) — Humanity's Last Exam 48.7, $10.0/1M tokens
Claude Opus 5 (Low) (Anthropic) — Humanity's Last Exam 43.4, $10.0/1M tokens
Claude Opus 4.7 (Max) (Anthropic) — Humanity's Last Exam 42.3, $10.0/1M tokens
Claude Opus 4.6 (Max) (Anthropic) — Humanity's Last Exam 39.9, $10.0/1M tokens
Claude Opus 4.7 (Non-reasoning, High) (Anthropic) — Humanity's Last Exam 33.3, $10.0/1M tokens
Claude Opus 4.5 (Reasoning) (Anthropic) — Humanity's Last Exam 30.1, $10.0/1M tokens
Claude Opus 4.6 (Non-reasoning, High) (Anthropic) — Humanity's Last Exam 19.1, $10.0/1M tokens
Claude Opus 4.5 (Non-reasoning) (Anthropic) — Humanity's Last Exam 13.2, $10.0/1M tokens
GPT-5.5 (Xhigh) (OpenAI) — Humanity's Last Exam 45.8, $11.25/1M tokens
GPT-5.5 (High) (OpenAI) — Humanity's Last Exam 45.0, $11.25/1M tokens
GPT-5.5 (Medium) (OpenAI) — Humanity's Last Exam 42.4, $11.25/1M tokens
GPT-5.5 (Low) (OpenAI) — Humanity's Last Exam 32.7, $11.25/1M tokens
GPT-5.5 Instant (May 2026) (OpenAI) — Humanity's Last Exam 21.6, $11.25/1M tokens
GPT-5.5 Instant (June 2026) (OpenAI) — Humanity's Last Exam 19.9, $11.25/1M tokens
GPT-5.5 (Non-reasoning) (OpenAI) — Humanity's Last Exam 13.7, $11.25/1M tokens
GPT-4 Turbo (OpenAI) — Humanity's Last Exam 3.1, $15.0/1M tokens
Claude Fable 5.1 (Max, Default Fallback) (Anthropic) — Humanity's Last Exam 59.1, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (Xhigh, Default Fallback) (Anthropic) — Humanity's Last Exam 58.7, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (High, Default Fallback) (Anthropic) — Humanity's Last Exam 55.9, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5 (Max, Opus 4.8 Fallback) (Anthropic) — Humanity's Last Exam 55.5, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Max) (OpenAI) — Humanity's Last Exam 54.7, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Xhigh) (OpenAI) — Humanity's Last Exam 54.6, $20.0/1M tokens (클릭: 관련 논문)
Claude Fable 5.1 (Medium, Default Fallback) (Anthropic) — Humanity's Last Exam 53.8, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (High) (OpenAI) — Humanity's Last Exam 53.1, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Medium) (OpenAI) — Humanity's Last Exam 52.7, $20.0/1M tokens (클릭: 관련 논문)
GPT-6 Astra (Low) (OpenAI) — Humanity's Last Exam 49.2, $20.0/1M tokens
Claude Fable 5.1 (Low, Default Fallback) (Anthropic) — Humanity's Last Exam 48.9, $20.0/1M tokens
o1 (OpenAI) — Humanity's Last Exam 7.0, $26.25/1M tokens
Claude 4.1 Opus (Reasoning) (Anthropic) — Humanity's Last Exam 12.5, $30.0/1M tokens
Claude 4 Opus (Reasoning) (Anthropic) — Humanity's Last Exam 12.3, $30.0/1M tokens
Claude 4 Opus (Non-reasoning) (Anthropic) — Humanity's Last Exam 6.2, $30.0/1M tokens
Claude 3 Opus (Anthropic) — Humanity's Last Exam 2.8, $30.0/1M tokens
Llama 3.1 Instruct 8B
Sarvam 30B
Qwen3.5 4B
Sarvam 105B
NVIDIA Nemotron 3 Nano 30B A3B
Hy3-preview
DeepSeek V4 Flash 0420
MiMo-V2.6-Flash
Claude Haiku 5.5
MiMo-V2.6-Pro
Gemini 4 Argon
Claude Opus 5.5
Artificial Analysis Intelligence Index
내림차순 ↓
MMLU-Pro·GPQA Diamond·HLE·LiveCodeBench·SciCode·AA-LCR·Terminal-Bench 등 10개 안팎의 평가를 Artificial Analysis가 가중 합성한 종합 지능 지수(0~100). 높을수록 전반적 성능이 좋습니다.
Index · 상위 25개 모델
· 리더보드에서 논문
결과와 비교 →
나머지 15개 보기
Artificial Analysis Coding Index
내림차순 ↓
LiveCodeBench·SciCode·Terminal-Bench 등 코딩 관련 평가만 합성한 지수(0~100). 코드 생성과 터미널 작업 수행 능력을 봅니다.
Index · 상위 25개 모델
· 리더보드에서 논문
결과와 비교 →
나머지 15개 보기
Humanity's Last Exam
내림차순 ↓
전 분야 전문가들이 출제한 최고 난도 시험(2,500+ 문항)의 정답률(%). 프런티어 모델도 수십 % 수준에 머무는 미포화 벤치마크입니다.
Accuracy · 상위 25개 모델
· 리더보드에서 논문
결과와 비교 →
나머지 15개 보기
Price per 1M Tokens (Blended 3:1)
지능 상위 25 · 비싼 순
내림차순 ↓
입력:출력 3:1 혼합 기준 1백만 토큰당 API 가격(USD). Intelligence Index 상위 25개 프런티어 모델만 대상으로, 같은 급 안에서 가격을 비교합니다 (기본 비싼 순).
USD per 1M Tokens · 상위 25개 모델
· 리더보드에서 논문
결과와 비교 →
나머지 15개 보기
데이터: Artificial Analysis (원본) · 본 미러는 표기 조건에 따라
출처를 명시하며, 행 단위 데이터는 각 벤치마크 리더보드 페이지에서도
"외부" 배지로 제공됩니다.