← ALL ARENAS

TEXT

General text and chat model performance

283 MODELS
gemini 3 Pro #1 MODEL
1491 TOP ELO
RANKMODELORGELO95% CI
1gemini 3 ProGoogle1491+6/-6
2grok-4.1-thinkingxAI1479+6/-5
3claude-opus-4-5-20251101-thinking-32kAnthropic1470+7/-7
4claude-opus-4-5-20251101Anthropic1464+6/-7
5grok-4.1xAI1463+6/-6
6gpt 5.1 HighOpenAI1457+7/-6
7gemini 2.5 ProGoogle1451+3/-4
8claude-sonnet-4-5-20250929-thinking-32kAnthropic1450+4/-5
9claude-opus-4-1-20250805-thinking-16kAnthropic1448+4/-4
10claude-sonnet-4-5-20250929Anthropic1446+4/-5
11gpt 4.5 Preview 2025 02 27OpenAI1442+6/-5
12claude-opus-4-1-20250805Anthropic1441+3/-4
13Chatgpt 4o Latest 20250326OpenAI1439+4/-3
14gpt 5.1OpenAI1436+6/-6
15gpt 5 HighOpenAI1436+5/-4
16qwen3-max-previewAlibaba1433+5/-4
17O3 2025 04 16OpenAI1433+4/-3
18grok-4-1-fast-reasoningxAI1430+6/-7
19ernie-5.0-preview-1103Baidu1429+9/-9
20kimi-k2-thinking-turboMoonshot1427+6/-6
21glm-4.6Z.ai1426+4/-5
22gpt 5 ChatOpenAI1425+4/-4
23qwen3-max-2025-09-23Alibaba1424+6/-7
24deepseek-v3.2-expDeepSeek AI1423+7/-6
25claude Opus 4 20250514 Thinking 16kAnthropic1423+4/-5
26deepseek-v3.2-thinkingDeepSeek AI1422+8/-8
27qwen3-235b-a22b-instruct-2507Alibaba1421+4/-3
28deepseek-v3.2-exp-thinkingDeepSeek AI1421+7/-7
29grok-4-fast-chatxAI1420+8/-7
30deepseek-r1-0528DeepSeek1418+6/-6
31kimi-k2-0905-previewMoonshot1418+6/-7
32deepseek-v3.1DeepSeek1416+6/-6
33kimi-k2-0711-previewMoonshot1416+5/-5
34deepseek-v3.1-thinkingDeepSeek1416+6/-7
35deepseek-v3.2DeepSeek AI1416+7/-8
36deepseek-v3.1-terminusDeepSeek AI1415+10/-9
37Qwen3 Vl 235b A22b InstructAlibaba1415+7/-7
38mistral-large-3Mistral1414+8/-7
39deepseek-v3.1-terminus-thinkingDeepSeek AI1413+10/-9
40gpt 4.1 2025 04 14OpenAI1412+4/-4
41claude Opus 4 20250514Anthropic1412+4/-4
42grok-3-preview-02-24xAI1410+4/-4
43Mistral Medium 2508Mistral1410+4/-4
44grok 4 0709xAI1409+3/-4
45glm-4.5Z.ai1408+5/-4
46gemini 2.5 FlashGoogle1408+3/-3
47gemini 2.5 Flash Preview 09 2025Google1405+4/-5
48claude-haiku-4-5-20251001Anthropic1402+5/-4
49grok-4-fast-reasoningxAI1402+5/-5
50qwen3-next-80b-a3b-instructAlibaba1400+5/-5
51longcat-flash-chatMeituan1400+6/-7
52O1 2024 12 17OpenAI1400+5/-4
53qwen3-235b-a22b-no-thinkingAlibaba1399+5/-4
54claude Sonnet 4 20250514 Thinking 32kAnthropic1399+4/-5
55qwen3-235b-a22b-thinking-2507Alibaba1397+6/-7
56deepseek-r1DeepSeek1395+5/-4
57Qwen3 Vl 235b A22b ThinkingAlibaba1394+6/-7
58deepseek-v3-0324DeepSeek1392+4/-4
59gpt 5 Mini HighOpenAI1392+5/-5
60O4 Mini 2025 04 16OpenAI1391+4/-4
61Hunyuan Vision 1.5 ThinkingTencent1391+12/-12
62mai-1-previewMicrosoft AI1390+6/-5
63claude Sonnet 4 20250514Anthropic1389+4/-4
64o1-previewOpenAI1387+5/-5
65claude 3 7 Sonnet 20250219 Thinking 32kAnthropic1387+4/-5
66qwen3-coder-480b-a35b-instructAlibaba1385+5/-5
67hunyuan-t1-20250711Tencent1385+8/-9
68Mistral Medium 2505Mistral1383+5/-5
69qwen3-30b-a3b-instruct-2507Alibaba1382+5/-5
70hunyuan-turbos-20250416Tencent1380+6/-6
71gpt 4.1 Mini 2025 04 14OpenAI1380+5/-4
72gemini 2.5 Flash Lite Preview 09 2025 No ThinkingGoogle1378+4/-5
73gemini 2.5 Flash Lite Preview 06 17 ThinkingGoogle1375+4/-5
74qwen3-235b-a22bAlibaba1374+5/-5
75qwen2.5-maxAlibaba1372+4/-4
76claude 3 7 Sonnet 20250219Anthropic1371+4/-4
77claude 3 5 Sonnet 20241022Anthropic1371+3/-3
78glm-4.5-airZ.ai1370+4/-4
79qwen3-next-80b-a3b-thinkingAlibaba1367+6/-6
80minimax-m1MiniMax1366+4/-4
81Gemma 3 27b ItGoogle1364+4/-3
82o3-mini-highOpenAI1362+5/-5
83grok-3-mini-highxAI1362+5/-5
84gemini 2.0 Flash 001Google1360+4/-4
85deepseek-v3DeepSeek1357+5/-5
86grok-3-mini-betaxAI1357+5/-5
87Mistral Small 2506Mistral1355+5/-5
88gpt-oss-120bOpenAI1352+5/-4
89command-a-03-2025Cohere1352+3/-4
90Glm 4.5vZ.ai1352+8/-8
91gemini 2.0 Flash Lite Preview 02 05Google1352+4/-4
92amazon-nova-experimental-chat-10-20Amazon1351+6/-7
93gemini 1.5 Pro 002Google1351+3/-4
94intellect-3Prime Intellect1350+10/-10
95o3-miniOpenAI1347+4/-3
96ling-flash-2.0Ant Group1346+7/-7
97hunyuan-turbos-20250226Tencent1346+11/-12
98minimax-m2MiniMax1346+7/-8
99Step 3StepFun1346+7/-8
100llama-3.1-nemotron-ultra-253b-v1Nvidia1345+12/-11
101amazon-nova-experimental-chat-10-09Amazon1345+11/-10
102qwen3-32bAlibaba1345+9/-10
103qwen-plus-0125Alibaba1344+8/-8
104gpt 4o 2024 05 13OpenAI1344+3/-3
105glm-4-plus-0111Zhipu1342+9/-8
106claude 3 5 Sonnet 20240620Anthropic1341+4/-3
107gemma-3-12b-itGoogle1340+10/-9
108nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia1340+10/-10
109hunyuan-turbo-0110Tencent1338+12/-11
110gpt 5 Nano HighOpenAI1338+7/-6
111nova-2-liteAmazon1337+8/-8
112o1-miniOpenAI1335+3/-4
113llama-3.1-405b-instruct-bf16Meta1335+3/-4
114qwq-32bAlibaba1334+4/-5
115gpt 4o 2024 08 06OpenAI1334+4/-4
116grok-2-2024-08-13xAI1333+4/-3
117llama-3.1-405b-instruct-fp8Meta1333+3/-4
118gemini-advanced-0514Google1332+6/-5
119step-2-16k-exp-202412StepFun1332+8/-9
120nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia1328+11/-11
121yi-lightning01 AI1327+5/-5
122llama 4 Maverick 17b 128e InstructMeta1327+4/-4
123qwen3-30b-a3bAlibaba1325+5/-4
124llama-3.3-nemotron-49b-super-v1Nvidia1325+12/-12
125hunyuan-large-2025-02-10Tencent1324+10/-9
126gpt 4 Turbo 2024 04 09OpenAI1323+4/-4
127deepseek-v2.5-1210DeepSeek1322+8/-9
128claude 3 5 Haiku 20241022Anthropic1322+3/-3
129llama 4 Scout 17b 16e InstructMeta1322+5/-4
130gemini 1.5 Pro 001Google1321+4/-4
131claude 3 Opus 20240229Anthropic1321+3/-3
132gpt 4.1 Nano 2025 04 14OpenAI1320+8/-7
133ring-flash-2.0Ant Group1319+8/-7
134llama-3.3-70b-instructMeta1319+3/-4
135Step 1o Turbo 202506StepFun1319+7/-6
136gemma-3n-e4b-itGoogle1318+5/-5
137gpt-oss-20bOpenAI1318+6/-7
138glm-4-plusZhipu AI1318+4/-5
139qwen-max-0919Alibaba1316+6/-5
140gpt 4o Mini 2024 07 18OpenAI1316+3/-4
141qwen2.5-plus-1127Alibaba1313+7/-6
142athene-v2-chatNexusFlow1313+4/-5
143mistral-large-2407Mistral1313+3/-4
144gpt-4-1106-previewOpenAI1312+4/-4
145gpt-4-0125-previewOpenAI1312+4/-4
146mercuryInception AI1311+14/-14
147olmo-3-32b-thinkAllen AI1310+10/-10
148hunyuan-standard-2025-02-10Tencent1310+9/-10
149gemini 1.5 Flash 002Google1309+5/-4
150grok-2-mini-2024-08-13xAI1306+4/-3
151deepseek-v2.5DeepSeek1305+5/-4
152magistral-medium-2506Mistral1304+7/-6
153mistral-large-2411Mistral1304+4/-4
154athene-70b-0725NexusFlow1304+5/-6
155Mistral Small 3.1 24b Instruct 2503Mistral1303+4/-4
156gemma-3-4b-itGoogle1302+10/-9
157qwen2.5-72b-instructAlibaba1301+4/-4
158llama-3.1-nemotron-70b-instructNvidia1297+7/-8
159Hunyuan Large VisionTencent1294+9/-9
160llama-3.1-70b-instructMeta1292+4/-3
161Amazon Nova Pro V1.0Amazon1288+4/-5
162jamba-1.5-largeAI21 Labs1287+8/-7
163gemma-2-27b-itGoogle1287+3/-4
164reka-core-20240904Reka AI1286+8/-7
165llama-3.1-tulu-3-70bAi21285+11/-10
166llama-3.1-nemotron-51b-instructNvidia1285+10/-10
167gpt-4-0314OpenAI1285+5/-5
168gemini 1.5 Flash 001Google1284+4/-5
169claude 3 Sonnet 20240229Anthropic1280+4/-4
170gemma-2-9b-it-simpoPrinceton1278+7/-7
171nemotron-4-340b-instructNvidia1277+5/-6
172command-r-plus-08-2024Cohere1276+7/-6
173llama-3-70b-instructMeta1275+3/-4
174gpt-4-0613OpenAI1274+4/-4
175mistral-small-24b-instruct-2501Mistral1273+6/-6
176glm-4-0520Zhipu AI1272+7/-7
177reka-flash-20240904Reka AI1272+7/-7
178qwen2.5-coder-32b-instructAlibaba1269+8/-8
179c4ai-aya-expanse-32bCohere1266+5/-5
180gemma-2-9b-itGoogle1264+4/-4
181deepseek-coder-v2DeepSeek AI1263+6/-6
182command-r-plusCohere1262+4/-5
183qwen2-72b-instructAlibaba1261+5/-5
184claude 3 Haiku 20240307Anthropic1260+4/-3
185gemini 1.5 Flash 8b 001Google1259+4/-5
186Amazon Nova Lite V1.0Amazon1259+5/-5
187phi-4Microsoft1255+4/-5
188olmo-2-0325-32b-instructAllen AI1252+11/-11
189command-r-08-2024Cohere1251+6/-7
190mistral-large-2402Mistral1241+4/-5
191amazon-nova-micro-v1.0Amazon1241+5/-5
192jamba-1.5-miniAI21 Labs1238+7/-7
193ministral-8b-2410Mistral1236+9/-9
194qwen1.5-110b-chatAlibaba1233+6/-5
195gemini-pro-dev-apiGoogle1233+7/-8
196hunyuan-standard-256kTencent1233+11/-12
197qwen1.5-72b-chatAlibaba1232+5/-5
198reka-flash-21b-20240226-onlineReka AI1232+8/-7
199mixtral-8x22b-instruct-v0.1Mistral1229+4/-5
200command-rCohere1227+4/-5
201reka-flash-21b-20240226Reka AI1226+5/-6
202c4ai-aya-expanse-8bCohere1223+7/-7
203gpt-3.5-turbo-0125OpenAI1223+5/-5
204llama-3-8b-instructMeta1222+4/-4
205mistral-mediumMistral1222+5/-5
206llama-3.1-tulu-3-8bAi21221+11/-10
207gemini-proGoogle1220+12/-12
208zephyr-orpo-141b-A35b-v0.1HuggingFace1212+11/-10
209yi-1.5-34b-chat01 AI1212+5/-5
210llama-3.1-8b-instructMeta1210+4/-4
211granite-3.1-8b-instructIBM1209+11/-11
212qwen1.5-32b-chatAlibaba1204+6/-6
213gpt-3.5-turbo-1106OpenAI1200+9/-8
214gemma-2-2b-itGoogle1198+4/-4
215phi-3-medium-4k-instructMicrosoft1197+5/-5
216mixtral-8x7b-instruct-v0.1Mistral1197+4/-5
217dbrx-instruct-previewDatabricks1195+6/-6
218internlm2_5-20b-chatInternLM1191+8/-7
219qwen1.5-14b-chatAlibaba1191+7/-7
220wizardlm-70bMicrosoft1183+10/-9
221granite-3.0-8b-instructIBM1183+9/-9
222yi-34b-chat01 AI1182+7/-6
223deepseek-llm-67b-chatDeepSeek AI1182+12/-11
224openchat-3.5-0106OpenChat1181+8/-8
225openchat-3.5OpenChat1181+9/-10
226granite-3.1-2b-instructIBM1180+11/-11
227snowflake-arctic-instructSnowflake1179+6/-6
228gemma-1.1-7b-itGoogle1179+6/-6
229tulu-2-dpo-70bAllenAI/UW1177+10/-10
230openhermes-2.5-mistral-7bNousResearch1174+11/-10
231vicuna-33bLMSYS1172+6/-6
232starling-lm-7b-betaNexusflow1171+8/-7
233phi-3-small-8k-instructMicrosoft1171+6/-6
234llama-2-70b-chatMeta1170+5/-5
235starling-lm-7b-alphaUC Berkeley1167+8/-8
236llama-3.2-3b-instructMeta1166+8/-7
237nous-hermes-2-mixtral-8x7b-dpoNousResearch1164+12/-12
238qwq-32b-previewAlibaba1158+12/-11
239granite-3.0-2b-instructIBM1156+8/-8
240llama2-70b-steerlm-chatNvidia1155+13/-13
241solar-10.7b-instruct-v1.0Upstage AI1152+13/-13
242dolphin-2.2.1-mistral-7bCognitive Computations1150+15/-16
243mistral-7b-instruct-v0.2Mistral1149+7/-6
244mpt-30b-chatMosaicML1149+12/-12
245wizardlm-13bMicrosoft1148+9/-9
246falcon-180b-chatTII1145+18/-17
247qwen1.5-7b-chatAlibaba1142+10/-9
248phi-3-mini-4k-instruct-june-2024Microsoft1142+6/-6
249llama-2-13b-chatMeta1141+7/-7
250vicuna-13bLMSYS1140+7/-7
251qwen-14b-chatAlibaba1137+11/-11
252codellama-34b-instructMeta1135+9/-9
253palm-2Google1135+9/-9
254gemma-7b-itGoogle1134+9/-10
255phi-3-mini-128k-instructMicrosoft1130+7/-7
256zephyr-7b-betaHuggingFace1130+9/-9
257phi-3-mini-4k-instructMicrosoft1128+6/-6
258zephyr-7b-alphaHuggingFace1126+16/-15
259guanaco-33bUW1126+12/-12
260smollm2-1.7b-instructHuggingFace1120+14/-14
261stripedhyena-nous-7bTogether AI1119+11/-11
262codellama-70b-instructMeta1118+18/-18
263vicuna-7bLMSYS1113+9/-9
264gemma-1.1-2b-itGoogle1113+7/-8
265llama-3.2-1b-instructMeta1113+7/-8
266mistral-7b-instructMistral1109+9/-10
267llama-2-7b-chatMeta1107+7/-7
268gemma-2b-itGoogle1090+11/-12
269qwen1.5-4b-chatAlibaba1090+9/-10
270olmo-7b-instructAllen AI1073+11/-11
271koala-13bUC Berkeley1068+10/-10
272alpaca-13bStanford1065+11/-12
273gpt4all-13b-snoozyNomic AI1063+16/-15
274mpt-7b-chatMosaicML1060+12/-12
275chatglm3-6bTsinghua1055+12/-11
276RWKV-4-Raven-14BRWKV1040+11/-12
277chatglm2-6bTsinghua1024+13/-14
278oasst-pythia-12bOpenAssistant1020+11/-11
279chatglm-6bTsinghua994+12/-13
280fastchat-t5-3bLMSYS989+13/-12
281dolly-v2-12bDatabricks977+14/-14
282llama-13bMeta968+16/-16
283stablelm-tuned-alpha-7bStability AI950+13/-13

Data sourced from LM Arena - Text