멀티모달 AI 순위: 비전 언어 모델

LMArena Vision Arena 점수 순위입니다. 사용자가 이미지를 올리고 질문한 뒤 익명 두 모델의 답변에 투표합니다.

종합 OCR(문자 인식) 도표 이해 숙제 이미지 캡션 개체 인식 이미지 창작 유머 영어 중국어
🏆 종합 1위데이터 2026년 10월 19일
Claude Fable 5 (High)Anthropic · 1325

2026년 10월 19일 게시된 LMArena Vision Arena 데이터에서 Anthropic의 Claude Fable 5 (High)이(가) 1325점(14,714표)으로 167개 모델 중 1위입니다.

전체 순위 · 종합

167개
전체 오픈 웨이트

기본은 LMArena 점수 내림차순, ±는 95% 신뢰구간의 절반입니다. 항목 열은 해당 세부 순위 점수이며 –는 점수 없음입니다.

# 모델 LMArena · 종합 항목별 점수 라이선스
점수 순위 투표 수 OCR(문자 인식) 도표 이해 숙제 이미지 캡션
1 Claude Fable 5 (High)Anthropic 1325±7 1 14,714 1337 1357 1361 – Proprietary
2 Claude Opus 5.5 (High)Anthropic 1321±12 2 3,035 1326 1345 1362 – Proprietary
3 Claude Opus 5 (High)Anthropic 1320±7 3 17,743 1329 1348 1338 – Proprietary
4 Claude Fable 5.1 (Max)Anthropic 1319±9 4 5,026 1327 1343 1345 – Proprietary
5 Claude Opus 4.7Anthropic 1317±7 5 23,139 1327 1336 1335 – Proprietary
6 Claude Opus 4.6 (High)Anthropic 1316±6 6 22,286 1326 1332 1337 – Proprietary
7 Gemini 3.8 Flash (High)Google 1315±10 7 4,645 1333 1345 1351 – Proprietary
8 Gemini 3.7 Flash (High)Google 1314±9 8 5,369 1322 1329 1320 – Proprietary
9 Claude Opus 4.7 (High)Anthropic 1313±7 9 22,731 1320 1336 1337 – Proprietary
10 Qwen3.8-MaxAlibaba 1313±7 10 9,957 1322 1323 1336 – Proprietary
11 Claude Opus 4.6Anthropic 1312±6 11 26,841 1326 1340 1327 – Proprietary
12 Muse Spark 1.3 (Max)Meta 1308±9 12 5,392 1319 1330 1296 – Proprietary
13 Gemini 3.5 Flash (High)Google 1308±7 13 13,862 1312 1318 1321 – Proprietary
14 Gemini 3.5 Flash (Medium)Google 1306±7 14 14,061 1317 1323 1330 – Proprietary
15 Muse SparkMeta 1306±9 15 5,865 1307 1309 1299 – Proprietary
16 Gemini 3 ProGoogle 1305±7 16 13,623 1310 1301 1315 1325 Proprietary
17 Muse Spark 1.2 (xHigh)Meta 1304±14 17 1,948 1313 1317 – – Proprietary
18 GPT-5.4 (High)OpenAI 1303±6 18 30,747 1312 1327 1336 – Proprietary
19 Muse Spark 1.3 (xHigh)Meta 1302±10 19 4,897 1309 1318 1296 – Proprietary
20 Gemini 3.6 Flash (High)Google 1299±8 20 8,979 1312 1314 1314 – Proprietary
21 GPT-5.5OpenAI 1297±6 21 28,781 1306 1325 1327 – Proprietary
22 Gemini 3.1 Pro PreviewGoogle 1296±5 22 47,114 1304 1311 1316 1345 Proprietary
23 Claude Opus 4.8 (High)Anthropic 1294±6 23 18,303 1303 1315 1337 – Proprietary
24 GLM-5.3-FlashZ.ai오픈 1294±6 24 16,254 1299 1317 1318 – MIT
25 GPT-5.5 (High)OpenAI 1293±6 25 27,067 1304 1317 1332 – Proprietary
26 Muse Spark 1.1Meta 1293±7 26 12,804 1301 1305 1287 – Proprietary
27 GPT-5.4OpenAI 1292±6 27 22,804 1299 1316 1309 – Proprietary
28 Claude Opus 4.8Anthropic 1289±6 28 18,800 1298 1302 1328 – Proprietary
29 GPT-6.1 Sol (Max)OpenAI 1288±13 29 2,330 1289 1306 1356 – Proprietary
30 Claude Sonnet 5.5 (xHigh)Anthropic 1287±13 30 2,564 1297 1329 1331 – Proprietary
31 Grok 4.5xAI 1287±7 31 12,599 1293 1304 1295 – Proprietary
32 Gemini 3 FlashGoogle 1285±5 32 39,131 1291 1290 1313 1281 Proprietary
33 Claude Sonnet 4.6Anthropic 1283±6 33 27,408 1296 1306 1311 – Proprietary
34 Kimi K2.6Moonshot AI오픈 1282±7 34 16,368 1291 1298 1310 – Modified MIT
35 GPT-5.6 Sol (xHigh)OpenAI 1281±7 35 11,439 1290 1305 1305 – Proprietary
36 GPT-6 Astra (Max)OpenAI 1280±10 36 4,012 1292 1297 1337 – Proprietary
37 Qwen3.7-PlusAlibaba 1278±7 37 14,212 1288 1292 1295 – Proprietary
38 DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek오픈 1278±10 38 4,100 1282 1297 1307 – MIT
39 Gemma 4 31BGoogle오픈 1276±6 39 40,219 1282 1283 1310 1218 Apache 2.0
40 Dola Seed 2.0 ProByteDance 1274±7 40 10,972 1284 1289 1284 – Proprietary
41 Claude Sonnet 5 (High)Anthropic 1273±7 41 14,034 1288 1293 1311 – Proprietary
42 Mistral Large 4Mistral AI 1272±19 42 1,008 1284 1288 – – Proprietary
43 GPT-5.6 Terra (xHigh)OpenAI 1271±7 43 11,842 1278 1295 1312 – Proprietary
44 Qwen3.8-27BAlibaba오픈 1269±8 44 7,614 1281 1285 1295 – Apache 2.0
45 Gemini 3.5 Flash-LiteGoogle 1269±8 45 9,238 1280 1284 1291 – Proprietary
46 Kimi K2.5 (Thinking)Moonshot AI오픈 1269±6 46 28,249 1276 1282 1297 1257 Modified MIT
47 GPT-5.2 Chat (20260210)OpenAI 1268±6 47 16,465 1275 1285 1286 – Proprietary
48 Gemini 3 Flash (Minimal)Google 1266±5 48 37,173 1272 1276 1298 1241 Proprietary
49 SStep 5 PreviewStepFun 1265±15 49 1,649 1282 1308 1265 – Proprietary
50 GLM-5V-TurboZ.ai 1264±5 50 42,757 1270 1286 1273 1264 Proprietary
51 Gemini 2.5 ProGoogle 1263±5 51 88,755 1270 1274 1281 1304 Proprietary
52 Grok 4.6 (High)xAI 1263±8 52 7,261 1272 1285 1283 – Proprietary
53 MiMo-V2.6-ProXiaomi오픈 1263±15 53 1,754 1270 1281 1264 – MIT
54 Qwen3.5-397B-A17BAlibaba오픈 1262±5 54 32,657 1271 1277 1292 1230 Apache 2.0
55 Grok 4.20 Beta (Reasoning, 0309)xAI 1262±6 55 26,796 1266 1267 1269 – Proprietary
56 Gemma 4 26B A4BGoogle오픈 1260±6 56 23,922 1268 1264 1293 1297 Apache 2.0
57 Grok 4.20 Multi-Agent Beta (0309)xAI 1259±6 57 24,532 1261 1261 1275 – Proprietary
58 GPT-5.6 Luna (xHigh)OpenAI 1257±7 58 11,055 1264 1273 1282 – Proprietary
59 MiMo-V2.6-FlashXiaomi오픈 1256±11 59 3,618 1270 1276 1283 – MIT
60 Kimi K2.5 (Instant)Moonshot AI오픈 1254±11 60 4,111 1259 1257 1264 – Modified MIT
61 Gemini 2.5 Flash Preview (09-2025)Google 1254±10 61 4,792 1255 1250 1283 – Proprietary
62 MiniMax-M3MiniMax오픈 1251±6 62 19,844 1259 1266 1268 – MiniMax Community License
63 GPT-5.5 InstantOpenAI 1250±9 63 7,590 1256 1273 1247 – Proprietary
64 GPT-5.1 (High)OpenAI 1250±8 64 9,848 1255 1264 1272 1252 Proprietary
65 ERNIE-5.0-Preview (1220)Baidu 1248±11 65 3,349 1250 1236 1253 – Proprietary
66 MiMo-V2.5Xiaomi오픈 1247±6 66 29,381 1256 1269 1262 – MIT
67 Qwen3-VL-235B-A22B-InstructAlibaba오픈 1247±7 67 12,724 1253 1255 1277 1281 Apache 2.0
68 GPT-5.2 (High)OpenAI 1246±6 68 19,022 1257 1265 1276 1267 Proprietary
69 GPT-5.4 mini (High)OpenAI 1245±6 69 25,734 1253 1266 1285 – Proprietary
70 Qwen3.5-122B-A10BAlibaba오픈 1244±7 70 13,236 1251 1249 1261 – Apache 2.0
71 ChatGPT-4o Latest (20250326)OpenAI 1243±5 71 23,400 1249 1255 1252 1224 Proprietary
72 Qwen3.5-27BAlibaba오픈 1241±5 72 30,272 1246 1249 1256 1170 Apache 2.0
73 Gemini 3.1 Flash-Lite PreviewGoogle 1240±6 73 27,657 1246 1242 1271 1259 Proprietary
74 GPT-6 Sol (Max)OpenAI 1240±11 74 3,221 1258 1270 1286 – Proprietary
75 TInkling-SmallThinking Machines오픈 1237±8 75 8,074 1243 1251 1257 – Apache 2.0
76 Gemini 2.5 FlashGoogle 1235±5 76 60,087 1237 1245 1244 1277 Proprietary
77 GPT-5.1OpenAI 1235±8 77 10,801 1241 1244 1243 1165 Proprietary
78 GPT-5 ChatOpenAI 1232±7 78 39,894 1246 1252 1278 1212 Proprietary
79 Grok 4.7 (xHigh)xAI 1231±11 79 3,736 1241 1254 1309 – Proprietary
80 Grok 4.3xAI 1229±6 80 27,901 1235 1241 1241 – Proprietary
81 GPT-5.2OpenAI 1229±6 81 20,100 1233 1246 1258 1174 Proprietary
82 MiMo-V2-OmniXiaomi 1228±7 82 10,650 1238 1256 1253 – Proprietary
83 Mistral Medium 3.5Mistral AI오픈 1222±9 83 5,375 1233 1254 1230 – Modified MIT
84 Mistral Large 3Mistral AI오픈 1220±8 84 9,254 1228 1240 1216 – Apache 2.0
85 GPT-6 Luna (Max)OpenAI 1216±11 85 3,662 1225 1245 1261 – Proprietary
86 o3 (2025-04-16)OpenAI 1214±7 86 45,567 1218 1220 1234 1210 Proprietary
87 Qwen-VL-Max (2025-08-13)Alibaba 1213±12 87 3,170 1236 1268 – – Proprietary
88 GPT-4.1 (2025-04-14)OpenAI 1210±7 88 40,998 1218 1215 1248 1207 Proprietary
89 Grok 4 (0709)xAI 1210±7 89 30,173 1195 1204 1170 1245 Proprietary
90 GPT-5 (High)OpenAI 1208±7 90 34,445 1215 1227 1227 1204 Proprietary
91 Qwen3-VL-235B-A22B-ThinkingAlibaba오픈 1207±12 91 2,387 1212 1214 1234 – Apache 2.0
92 NNVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)NVIDIA오픈 1205±13 92 2,509 1216 1223 1229 – OpenMDW-1.1
93 GPT-5 mini (High)OpenAI 1202±8 93 28,943 1199 1202 1210 1217 Proprietary
94 Grok 4.1 Fast (Reasoning)xAI 1201±7 94 13,368 1195 1210 1172 – Proprietary
95 Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)Google 1198±9 95 4,862 1203 1197 1215 – Proprietary
96 GPT-5.4 nano (High)OpenAI 1196±6 96 25,624 1204 1210 1225 – Proprietary
97 GPT-4.5 Preview (2025-02-27)OpenAI 1195±12 97 2,925 – – – – Proprietary
98 o4-mini (2025-04-16)OpenAI 1194±7 98 41,316 1197 1197 1234 1204 Proprietary
99 Claude Opus 4 (Thinking 16K, 20250514)Anthropic 1192±16 99 1,290 1197 1179 1197 – Proprietary
100 Claude Sonnet 4 (Thinking 32K, 20250514)Anthropic 1191±17 100 1,144 1197 1200 – – Proprietary
101 Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)Google 1187±7 101 35,914 1188 1186 1190 1184 Proprietary
102 SStep-1o Turbo (202506)StepFun 1186±14 102 1,895 1177 1185 1155 – Proprietary
103 GPT-4.1 mini (2025-04-14)OpenAI 1181±7 103 40,201 1188 1182 1214 1174 Proprietary
104 Hunyuan Large VisionTencent 1180±16 104 1,274 1167 1135 – – Proprietary
105 Hunyuan Vision 1.5 ThinkingTencent 1180±12 105 2,424 1176 1194 1241 – Proprietary
106 SStep-3StepFun오픈 1176±12 106 3,193 1168 1155 1183 – Apache 2.0
107 Claude Opus 4 (20250514)Anthropic 1176±13 107 2,172 1179 1177 1228 – Proprietary
108 Claude Sonnet 4 (20250514)Anthropic 1175±14 108 1,806 1173 1178 1215 – Proprietary
109 Mistral Medium 3.1 (2508)Mistral AI 1172±6 109 41,611 1175 1175 1165 1145 Proprietary
110 Claude 3.7 Sonnet (Thinking 32K, 20250219)Anthropic 1169±16 110 1,436 1181 1176 1192 – Proprietary
111 o1 (2024-12-17)OpenAI 1168±11 111 3,694 – – – – Proprietary
112 Gemma 3 27B ITGoogle오픈 1165±8 112 16,982 1156 1156 1160 1151 Gemma
113 GLM-4.6VZ.ai오픈 1164±14 113 2,455 1171 1182 1155 – MIT
114 Gemini 1.5 Pro (002)Google 1161±9 114 8,902 – – – – Proprietary
115 GPT-5 nano (High)OpenAI 1159±11 115 3,928 1152 1141 1157 – Proprietary
116 Gemini 2.0 Flash (001)Google 1158±7 116 10,135 1148 1149 1175 1130 Proprietary
117 Mistral Medium 3 (2505)Mistral AI 1157±8 117 10,793 1154 1155 1165 1094 Proprietary
118 GLM-4.5VZ.ai오픈 1154±12 118 3,243 1151 1151 1163 – MIT
119 Qwen2.5-VL-32B-InstructAlibaba오픈 1152±15 119 1,490 – – – – Apache 2.0
120 Claude 3.7 Sonnet (20250219)Anthropic 1151±9 120 4,517 1157 1153 1206 – Proprietary
121 Mistral Small 3.2 (2506)Mistral AI오픈 1142±9 121 10,843 1134 1125 1173 1059 Apache 2.0
122 Llama 4 Maverick 17B 128E InstructMeta오픈 1142±9 122 6,923 1143 1134 1164 – Llama 4
123 Gemini 1.5 Flash (002)Google 1141±10 123 7,241 – – – – Proprietary
124 GPT-4o (2024-05-13)OpenAI 1137±9 124 23,273 – – – – Proprietary
125 Mistral Small 3.1 24B Instruct (2503)Mistral AI오픈 1136±8 125 28,490 1132 1119 1158 1153 Apache 2.0
126 Claude 3.5 Sonnet (20241022)Anthropic 1126±8 126 10,374 1139 1134 1136 – Proprietary
127 SStep-1o Vision 32K (High Res)StepFun 1122±13 127 2,833 – – – – Proprietary
128 Claude 3.5 Sonnet (20240620)Anthropic 1120±10 128 21,624 – – – – Proprietary
129 Llama 4 Scout 17B 16E InstructMeta오픈 1118±9 129 6,446 1117 1125 1148 – Llama
130 Qwen2.5-VL-72B-InstructAlibaba오픈 1107±11 130 3,768 – – – – Qwen
131 Gemini 2.0 Flash-Lite Preview (02-05)Google 1100±11 131 3,991 – – – – Proprietary
132 Claude 3.5 Haiku (20241022)Anthropic 1093±16 132 1,398 1091 1077 1119 – Proprietary
133 GPT-4 Turbo (2024-04-09)OpenAI 1090±12 133 13,391 – – – – Proprietary
134 Pixtral Large (2411)Mistral AI오픈 1089±9 134 5,423 – – – – MRL
135 Gemini 1.5 Pro (001)Google 1088±12 135 16,734 – – – – Proprietary
136 Molmo 2 8BAi2오픈 1081±20 136 1,190 1058 1072 1069 – Apache 2.0
137 GPT-4o mini (2024-07-18)OpenAI 1066±8 137 17,341 – – – – Proprietary
138 GPT-4o (2024-08-06)OpenAI 1065±12 138 3,376 – – – – Proprietary
139 GPT-4.1 nano (2025-04-14)OpenAI 1063±18 139 1,211 – – – – Proprietary
140 Qwen-VL-Max (1119)Alibaba 1058±16 140 1,422 – – – – Proprietary
141 Qwen2-VL-72BAlibaba오픈 1047±10 141 5,937 – – – – Qwen
142 SStep-1V 32KStepFun 1046±17 142 1,534 – – – – Proprietary
143 Gemini 1.5 Flash-8B (001)Google 1044±11 143 6,243 – – – – Proprietary
144 Claude 3 Opus (20240229)Anthropic 1023±10 144 15,565 – – – – Proprietary
145 Molmo 72B (0924)Ai2오픈 1012±13 145 3,048 – – – – Apache 2.0
146 Pixtral 12B (2409)Mistral AI오픈 1009±10 146 7,511 – – – – Apache 2.0
147 Gemini 1.5 Flash (001)Google 1008±12 147 13,260 – – – – Proprietary
148 OInternVL2 26BOpenGVLab오픈 1005±13 148 5,148 – – – – MIT
149 Llama 3.2 90B Vision InstructMeta오픈 1000±9 149 8,682 – – – – Llama 3.2
150 Hunyuan Standard Vision (2024-12-31)Tencent 999±21 150 809 – – – – Proprietary
151 Aya Vision 32BCohere오픈 996±22 151 847 – – – – CC-BY-NC-4.0
152 AAmazon Nova Lite 1.0Amazon 990±15 152 1,854 – – – – Proprietary
153 Qwen2-VL-7B-InstructAlibaba오픈 990±11 153 5,766 – – – – Apache 2.0
154 Claude 3 Sonnet (20240229)Anthropic 984±11 154 12,314 – – – – Proprietary
155 AAmazon Nova Pro 1.0Amazon 980±14 155 2,335 – – – – Proprietary
156 0Yi Vision01.AI 978±18 156 1,219 – – – – Proprietary
157 Llama 3.2 11B Vision InstructMeta오픈 966±11 157 4,817 – – – – Llama 3.2
158 Molmo 7B-D (0924)Ai2오픈 959±14 158 2,815 – – – – Apache 2.0
159 Claude 3 Haiku (20240307)Anthropic 950±13 159 13,380 – – – – Proprietary
160 OInternVL2 4BOpenGVLab오픈 941±13 160 3,703 – – – – MIT
161 Nnvila-internal-15b-v1NVIDIA오픈 940±20 161 1,077 – – – – -
162 LLLaVA 1.6 34B오픈 936±12 162 4,531 – – – – Apache 2.0
163 CogVLM2 Llama3 Chat 19BZ.ai오픈 928±15 163 1,991 – – – – CogVLM2
164 LLLaVA-OneVision Qwen2 72B OV오픈 923±18 164 1,321 – – – – Apache 2.0
165 OMiniCPM-V 2.6OpenBMB오픈 912±16 165 1,987 – – – – Apache 2.0
166 MPhi-3.5 Vision InstructMicrosoft오픈 851±16 166 2,592 – – – – MIT
167 MPhi-3 Vision 128K InstructMicrosoft오픈 812±19 167 1,401 – – – – MIT

점수: LMArena leaderboard-dataset(lmarena-ai, Hugging Face, CC-BY-4.0, vision 설정), 종합 게시일 2026년 10월 19일. 인용 시 출처를 밝혀 주세요.

데이터 출처와 산출 방법

  1. 점수는 같은 이미지 질문에 대한 익명 두 답변에 사람이 투표한 결과를 Bradley-Terry 모델로 추정한 Arena 점수입니다.
  2. 항목(OCR, 도표, 숙제, 캡션, 중국어/영어 등)은 프롬프트 유형별로 LMArena가 따로 계산한 순위이며 종합 점수의 분해가 아닙니다.
  3. 공개 데이터가 없는 항목(가격, 컨텍스트, 출시일 등)은 표시하지 않으며 빈칸은 –입니다. 추정하지 않습니다.
  4. 매일 자동 동기화. JSON API: /api/public/vision-leaderboard.php

자주 묻는 질문

현재 가장 강한 비전 언어 모델은?

2026년 10월 19일 게시된 LMArena Vision Arena 데이터에서 Anthropic의 Claude Fable 5 (High)이(가) 1325점(14,714표)으로 167개 모델 중 1위입니다.

회사별 최고 비전 모델은?

종합 순위 회사별 1위: Anthropic Claude Fable 5 (High) (1325, #1), Google Gemini 3.8 Flash (High) (1315, #7), Alibaba Qwen3.8-Max (1313, #10), Meta Muse Spark 1.3 (Max) (1308, #12), OpenAI GPT-5.4 (High) (1303, #18).

OCR이 가장 뛰어난 모델은?

LMArena OCR 순위(123개 모델) 1위는 Claude Fable 5 (High), 1337점입니다.

가장 강한 오픈 웨이트 비전 모델은?

오픈 웨이트 모델 50개 중 1위는 GLM-5.3-Flash(1294점, MIT)입니다.

MMMU 같은 벤치마크와 무엇이 다른가요?

MMMU 등은 고정 문제의 자동 채점이고, 이 순위는 사용자 자신의 이미지·질문에 대한 블라인드 투표로 실제 사용 선호를 반영합니다. 서로 환산할 수 없습니다.