Benchmark

Text Arena (arena.ai)

Measures: Users send a prompt to two anonymous models and vote for the better answer; votes are turned into an Elo-scale score with a confidence interval, style-controlled by default (a Factuality adjustment is optional).

Maintainer
Arena Intelligence (arena.ai; formerly LMArena / LMSYS Chatbot Arena)
Introduced
2023
Status
Active
Saturation
Headroom
Typical provenance
Independent
In scoring set
Yes

PaperOfficial leaderboard

Leaderboard

Independent and third-party results only.

Leaderboard
ModelArena score (Elo scale)Score CI (+/-)VotesProvenanceSourceEvaluated
Claude Opus 5.5
Anthropic · High effort
1509—2307IndependentArena25 Sep 2026
Claude Opus 4.6
Anthropic · High effort
1505—76518IndependentArena25 Sep 2026
Claude Fable 5
Anthropic · High effort
1504—36462IndependentArena25 Sep 2026
Claude Opus 4.7
Anthropic · High effort
1502—64007IndependentArena25 Sep 2026
Claude Fable 5.1
Anthropic · Max effort
1501—9942IndependentArena25 Sep 2026
Claude Opus 4.61498—80836IndependentArena25 Sep 2026
Claude Opus 4.71495—65051IndependentArena25 Sep 2026
Muse Spark 1.3
Meta · Max effort
1494—10036IndependentArena25 Sep 2026
Gemini 3.8 Flash
Google DeepMind · High effort
1492—21728IndependentArena25 Sep 2026
Claude Opus 5
Anthropic · High effort
1491—55063IndependentArena25 Sep 2026
Muse Spark 1.11491—34760IndependentArena25 Sep 2026
Claude Opus 5
Anthropic · Max effort
1488—26760IndependentArena25 Sep 2026
Gemini 3.7 Flash
Google DeepMind · High effort
1488—19044IndependentArena25 Sep 2026
Kimi K3
Moonshot AI · Max effort
1488—26400IndependentArena25 Sep 2026
Gemini 3.1 Pro1487—119196IndependentArena25 Sep 2026
Gemini 3 Pro1485—41921IndependentArena25 Sep 2026
GPT-5.6 Sol
OpenAI · Xhigh effort
1483—34258IndependentArena25 Sep 2026
Gemini 3.6 Flash
Google DeepMind · High effort
1482—33739IndependentArena25 Sep 2026
GPT-5.5
OpenAI · High effort
1481—69008IndependentArena25 Sep 2026
Claude Opus 4.8
Anthropic · High effort
1480—61560IndependentArena25 Sep 2026
MiMo-V2.6-Pro1480—4026IndependentArena25 Sep 2026
GLM-5.3
Z.ai (Zhipu AI) · Max effort
1480—15904IndependentArena25 Sep 2026
Qwen3.8-Max
Alibaba Group · Max effort
1479—21561IndependentArena25 Sep 2026
GPT-6 Astra
OpenAI · Max effort
1478—7185IndependentArena25 Sep 2026
Gemini 3.5 Flash
Google DeepMind · High effort
1477—46190IndependentArena25 Sep 2026
GPT-5.51477—70635IndependentArena25 Sep 2026
DeepSeek-V4.1-Flash
DeepSeek · Max effort
1477—6630IndependentArena25 Sep 2026
GPT-5.2 Instant (gpt-5.2-chat-latest)1476—35962IndependentArena25 Sep 2026
GLM-5.2
Z.ai (Zhipu AI) · Max effort
1476—43570IndependentArena25 Sep 2026
GPT-5.4
OpenAI · High effort
1475—64479IndependentArena25 Sep 2026
Qwen3.7-Max1475—3924IndependentArena25 Sep 2026
GLM-5.3-Flash1474—19103IndependentArena25 Sep 2026
Gemini 3.5 Flash
Google DeepMind · Medium effort
1474—44906IndependentArena25 Sep 2026
Claude Opus 4.81474—62717IndependentArena25 Sep 2026
Gemini 3 Flash1473—31283IndependentArena25 Sep 2026
Claude Sonnet 4.61472—70662IndependentArena25 Sep 2026
Grok 4.20
SpaceXAI (xAI) · Reasoning effort
1471—66222IndependentArena25 Sep 2026
Grok 4.20 Multi-Agent1470—64674IndependentArena25 Sep 2026
Claude Opus 4.51470—72766IndependentArena25 Sep 2026
ERNIE 5.11468—39423IndependentArena25 Sep 2026
MiMo-V2.5-Pro1467—69225IndependentArena25 Sep 2026
Grok 4.51465—37535IndependentArena25 Sep 2026
Grok 4.1
SpaceXAI (xAI) · Thinking effort
1465—66407IndependentArena25 Sep 2026
GLM-5.11465—56463IndependentArena25 Sep 2026
GPT-5.6 Terra
OpenAI · Xhigh effort
1465—35323IndependentArena25 Sep 2026
GPT-5.41465—67632IndependentArena25 Sep 2026
DeepSeek-V4-Pro1464—9857IndependentArena25 Sep 2026
Claude Sonnet 5
Anthropic · High effort
1462—43340IndependentArena25 Sep 2026
Kimi K2.61461—39971IndependentArena25 Sep 2026
Qwen3.6-Max-Preview1460—5414IndependentArena25 Sep 2026
Grok 4.11459—68507IndependentArena25 Sep 2026
DeepSeek-V4-Pro1458—57564IndependentArena25 Sep 2026
GPT-6 Sol
OpenAI · Max effort
1457—4773IndependentArena25 Sep 2026
GLM-51457—29152IndependentArena25 Sep 2026
Hy31457—9839IndependentArena25 Sep 2026
Gemini 3.5 Flash-Lite1456—33501IndependentArena25 Sep 2026
Qwen3.7-Plus1456—42031IndependentArena25 Sep 2026
GPT-5.1
OpenAI · High effort
1456—41596IndependentArena25 Sep 2026
Claude Sonnet 4.51455—82451IndependentArena25 Sep 2026
GPT-5.6 Luna
OpenAI · Xhigh effort
1454—35823IndependentArena25 Sep 2026
MiMo-V2.6-Flash1454—4067IndependentArena25 Sep 2026
Grok 4.6
SpaceXAI (xAI) · High effort
1453—21380IndependentArena25 Sep 2026
Gemma 4 31B1453—6135IndependentArena25 Sep 2026
Kimi K2.5
Moonshot AI · Thinking effort
1450—74638IndependentArena25 Sep 2026
GPT-5.3 Instant (gpt-5.3-chat-latest)1450—34309IndependentArena25 Sep 2026
ERNIE 5.01449—9793IndependentArena25 Sep 2026
Claude Opus 4.11448—76940IndependentArena25 Sep 2026
MiMo-V2-Pro1448—25423IndependentArena25 Sep 2026
GPT-5.4 mini
OpenAI · High effort
1447—63140IndependentArena25 Sep 2026
ERNIE 5.01447—36434IndependentArena25 Sep 2026
Gemini 2.5 Pro1446—124887IndependentArena25 Sep 2026
GPT-4.51445—14547IndependentArena25 Sep 2026
Qwen3.6-Plus1443—48095IndependentArena25 Sep 2026
ChatGPT-4o1443—81607IndependentArena25 Sep 2026
GPT-6 Luna
OpenAI · Max effort
1442—4792IndependentArena25 Sep 2026
Inkling1442—32778IndependentArena25 Sep 2026
Qwen3.5-397B-A17B1442—86319IndependentArena25 Sep 2026
Grok 4.31442—71054IndependentArena25 Sep 2026
GLM-4.71441—12217IndependentArena25 Sep 2026
MiniMax-M31440—56646IndependentArena25 Sep 2026
Grok 4.7
SpaceXAI (xAI) · Xhigh effort
1439—4114IndependentArena25 Sep 2026
GPT-5.11438—44329IndependentArena25 Sep 2026
Qwen3.8-27B1438—16383IndependentArena25 Sep 2026
Gemma 4 26B A4B1438—6078IndependentArena25 Sep 2026
GPT-5.2
OpenAI · High effort
1437—49570IndependentArena25 Sep 2026
DeepSeek-V4-Flash1436—51871IndependentArena25 Sep 2026
GPT-5.21436—83555IndependentArena25 Sep 2026
Qwen3-Max1435—27235IndependentArena25 Sep 2026
GPT-5
OpenAI · High effort
1435—31503IndependentArena25 Sep 2026
MiMo-V2.51434—47276IndependentArena25 Sep 2026
GLM-5V-Turbo1433—10393IndependentArena25 Sep 2026
Gemini 3.1 Flash-Lite1433—63931IndependentArena25 Sep 2026
o31432—58587IndependentArena25 Sep 2026
MiMo-V2-Omni1431—20611IndependentArena25 Sep 2026
Grok 4.1 Fast
SpaceXAI (xAI) · Reasoning effort
1430—57452IndependentArena25 Sep 2026
Kimi K2 Thinking1430—63241IndependentArena25 Sep 2026
GPT-5 Instant (gpt-5-chat-latest)1427—31012IndependentArena25 Sep 2026
Mistral Medium 3.51426—11693IndependentArena25 Sep 2026
DeepSeek-V3.2-Exp
DeepSeek · Thinking effort
1425—8942IndependentArena25 Sep 2026
DeepSeek-V3.21425—48010IndependentArena25 Sep 2026
GLM-4.61424—35678IndependentArena25 Sep 2026
Qwen3-Max1423—8969IndependentArena25 Sep 2026
DeepSeek-V3.2
DeepSeek · Thinking effort
1423—41980IndependentArena25 Sep 2026
Qwen3-235B-A22B-Instruct-25071422—97815IndependentArena25 Sep 2026
DeepSeek-V3.2-Exp1422—11947IndependentArena25 Sep 2026
DeepSeek-R11422—18065IndependentArena25 Sep 2026
Kimi K21419—11537IndependentArena25 Sep 2026
ERNIE 5.01418—4728IndependentArena25 Sep 2026
Kimi K21418—26960IndependentArena25 Sep 2026
DeepSeek-V3.1-Terminus
DeepSeek · Thinking effort
1417—3351IndependentArena25 Sep 2026
DeepSeek-V3.11417—14543IndependentArena25 Sep 2026
Qwen3.5-122B-A10B1416—29671IndependentArena25 Sep 2026
DeepSeek-V3.1
DeepSeek · Thinking effort
1416—11408IndependentArena25 Sep 2026
GPT-4.11415—50001IndependentArena25 Sep 2026
MiniMax-M2.71415—77968IndependentArena25 Sep 2026
DeepSeek-V3.1-Terminus1415—3600IndependentArena25 Sep 2026
Claude Opus 41414—42789IndependentArena25 Sep 2026
Claude Haiku 4.51414—140791IndependentArena25 Sep 2026
Qwen3-VL-235B-A22B-Instruct1413—11241IndependentArena25 Sep 2026
Mistral Large 31413—77456IndependentArena25 Sep 2026
GLM-4.51411—23659IndependentArena25 Sep 2026
Grok 41411—39389IndependentArena25 Sep 2026
Gemini 2.5 Flash1409—125044IndependentArena25 Sep 2026
Qwen3.5-27B1409—28640IndependentArena25 Sep 2026
Mistral Medium 3.11408—95010IndependentArena25 Sep 2026
Inkling Small1405—24758IndependentArena25 Sep 2026
Grok 4 Fast
SpaceXAI (xAI) · Reasoning effort
1405—18151IndependentArena25 Sep 2026
Gemini 2.5 Flash1403—32853IndependentArena25 Sep 2026
o11402—27807IndependentArena25 Sep 2026
LongCat-Flash-Chat1401—11119IndependentArena25 Sep 2026
GPT-5.4 nano
OpenAI · High effort
1401—62171IndependentArena25 Sep 2026
Qwen3-235B-A22B-Thinking-25071400—8776IndependentArena25 Sep 2026
Qwen3-Next-80B-A3B-Instruct1399—22602IndependentArena25 Sep 2026
DeepSeek-R11398—18524IndependentArena25 Sep 2026
Qwen3.5-Flash1396—61728IndependentArena25 Sep 2026
Qwen3-VL-235B-A22B-Thinking
Alibaba Group · Thinking effort
1395—7797IndependentArena25 Sep 2026
Qwen3.5-35B-A3B1394—30420IndependentArena25 Sep 2026
Step 3.5 Flash1393—60243IndependentArena25 Sep 2026
o4-mini1391—44637IndependentArena25 Sep 2026
MiniMax-M2.51391—42743IndependentArena25 Sep 2026
Claude Sonnet 41391—38917IndependentArena25 Sep 2026
GPT-5 mini
OpenAI · High effort
1390—26641IndependentArena25 Sep 2026
o1-preview1389—31122IndependentArena25 Sep 2026
Mistral Medium 31387—32615IndependentArena25 Sep 2026
Qwen3-Coder-480B-A35B-Instruct1387—25012IndependentArena25 Sep 2026
Solar Pro 41385—13541IndependentArena25 Sep 2026
GPT-4.1 mini1383—38547IndependentArena25 Sep 2026
Qwen3-30B-A3B-Instruct-25071383—23179IndependentArena25 Sep 2026
Trinity Large (Preview)1379—31227IndependentArena25 Sep 2026
GLM-4.6V1379—2830IndependentArena25 Sep 2026
Qwen3-235B-A22B1375—25827IndependentArena25 Sep 2026
Gemini 2.5 Flash-Lite
Google DeepMind · Thinking effort
1375—32185IndependentArena25 Sep 2026
Claude 3.5 Sonnet1374—87644IndependentArena25 Sep 2026
Qwen2.5-Max
Alibaba Group · Max effort
1374—32410IndependentArena25 Sep 2026
GLM-4.5-Air1373—30453IndependentArena25 Sep 2026
Claude 3.7 Sonnet1373—42408IndependentArena25 Sep 2026
Qwen3-Next-80B-A3B-Thinking
Alibaba Group · Thinking effort
1369—13373IndependentArena25 Sep 2026
Trinity Large Thinking
Arcee AI · Thinking effort
1368—30277IndependentArena25 Sep 2026
Gemma 3 27B1365—46433IndependentArena25 Sep 2026
GLM-4.7-Flash1365—11983IndependentArena25 Sep 2026
MiniMax-M11364—34045IndependentArena25 Sep 2026
Grok 3 Mini
SpaceXAI (xAI) · High effort
1364—15505IndependentArena25 Sep 2026
o3-mini
OpenAI · High effort
1364—18589IndependentArena25 Sep 2026
Gemini 2.0 Flash1360—43315IndependentArena25 Sep 2026
DeepSeek-V31358—21770IndependentArena25 Sep 2026
Grok 3 Mini1358—20813IndependentArena25 Sep 2026
Mistral Small 3.21357—17352IndependentArena25 Sep 2026
Command A1354—55477IndependentArena25 Sep 2026
Gemini 2.0 Flash-Lite1354—24955IndependentArena25 Sep 2026
GLM-4.5V1352—4809IndependentArena25 Sep 2026
gpt-oss-120b1352—30021IndependentArena25 Sep 2026
Gemini 1.5 Pro1351—55606IndependentArena25 Sep 2026
Step31349—6267IndependentArena25 Sep 2026
o3-mini1348—56572IndependentArena25 Sep 2026
Llama 3.1 Nemotron Ultra 253B v11348—2549IndependentArena25 Sep 2026
Qwen3-32B1347—3926IndependentArena25 Sep 2026
GPT-4o1346—112881IndependentArena25 Sep 2026
Ling-flash-2.01344—6889IndependentArena25 Sep 2026
MiniMax-M21343—6817IndependentArena25 Sep 2026
Claude 3.5 Sonnet1343—82419IndependentArena25 Sep 2026
Mercury 21343—3200IndependentArena25 Sep 2026
Gemma 3 12B1342—3829IndependentArena25 Sep 2026
Granite 4.2 30B1341—3385IndependentArena25 Sep 2026
GPT-5 nano
OpenAI · High effort
1338—8111IndependentArena25 Sep 2026
o1-mini1337—51981IndependentArena25 Sep 2026
QwQ-32B1336—25080IndependentArena25 Sep 2026
Grok 21336—63498IndependentArena25 Sep 2026
GPT-4o1336—45499IndependentArena25 Sep 2026
Amazon Nova 2 Lite1335—12396IndependentArena25 Sep 2026
Olmo 3.1 32B Instruct1329—11798IndependentArena25 Sep 2026
Yi-Lightning1328—27332IndependentArena25 Sep 2026
Llama 4 Maverick1327—39266IndependentArena25 Sep 2026
Qwen3-30B-A3B1327—26041IndependentArena25 Sep 2026
Hunyuan-Large1326—3738IndependentArena25 Sep 2026
Claude 3.5 Haiku1325—68875IndependentArena25 Sep 2026
GPT-4 Turbo1324—98114IndependentArena25 Sep 2026
Gemini 1.5 Pro1324—79138IndependentArena25 Sep 2026
DeepSeek-V2.51323—6795IndependentArena25 Sep 2026
Ring-flash-2.01322—6933IndependentArena25 Sep 2026
GPT-4.1 nano1322—6103IndependentArena25 Sep 2026
Claude 3 Opus1322—194909IndependentArena25 Sep 2026
Llama 4 Scout1322—29673IndependentArena25 Sep 2026
GLM-4-Plus1319—26126IndependentArena25 Sep 2026
Qwen-Max (2024)1318—16478IndependentArena25 Sep 2026
Llama 3.3 70B1318—54368IndependentArena25 Sep 2026
GPT-4o mini1318—68697IndependentArena25 Sep 2026
gpt-oss-20b1318—10372IndependentArena25 Sep 2026
Gemma 3n E4B1317—22041IndependentArena25 Sep 2026
Mistral Large 2.01314—45459IndependentArena25 Sep 2026
Nemotron 3 Nano 30B-A3B1313—15731IndependentArena25 Sep 2026
GPT-4 Turbo1313—93439IndependentArena25 Sep 2026
GPT-4 Turbo1313—100105IndependentArena25 Sep 2026
Gemini 1.5 Flash1309—34902IndependentArena25 Sep 2026
Grok 2 mini1308—52567IndependentArena25 Sep 2026
DeepSeek-V2.51307—24572IndependentArena25 Sep 2026
Olmo 3 32B Think1306—5817IndependentArena25 Sep 2026
Mistral Large 2.11306—28073IndependentArena25 Sep 2026
Mercury1305—1951IndependentArena25 Sep 2026
Magistral Medium 1.01305—11435IndependentArena25 Sep 2026
Granite 4.1 8B1304—4168IndependentArena25 Sep 2026
Gemma 3 4B1303—4171IndependentArena25 Sep 2026
Mistral Small 3.11303—32548IndependentArena25 Sep 2026
Qwen2.5-72B-Instruct1303—39406IndependentArena25 Sep 2026
Llama 3.1 70B1293—55240IndependentArena25 Sep 2026
Granite 4.2 3B1292—3237IndependentArena25 Sep 2026
Gemma 2 27B1289—75754IndependentArena25 Sep 2026
Jamba 1.5 Large1289—8662IndependentArena25 Sep 2026
Granite 4.2 8B1289—3218IndependentArena25 Sep 2026
Reka Core1288—7312IndependentArena25 Sep 2026
GPT-41288—54173IndependentArena25 Sep 2026
Llama-3.1-Nemotron-51B-Instruct1287—3749IndependentArena25 Sep 2026
Gemini 1.5 Flash1287—62833IndependentArena25 Sep 2026
Olmo 3.1 32B Think1287—8285IndependentArena25 Sep 2026
Llama 3.1 Tulu 3 70B1286—2846IndependentArena25 Sep 2026
Claude 3 Sonnet1281—109284IndependentArena25 Sep 2026
Nemotron-4 340B1277—19659IndependentArena25 Sep 2026
Command R+ (08-2024)1276—9866IndependentArena25 Sep 2026
GPT-41276—88723IndependentArena25 Sep 2026
Mistral Small 3.01274—14681IndependentArena25 Sep 2026
GLM-41273—9788IndependentArena25 Sep 2026
Qwen2.5-Coder-32B-Instruct1271—5432IndependentArena25 Sep 2026
Aya Expanse 32B1267—27124IndependentArena25 Sep 2026
Gemma 2 9B1267—54611IndependentArena25 Sep 2026
DeepSeek-Coder-V21265—15147IndependentArena25 Sep 2026
Qwen2-72B-Instruct1262—37325IndependentArena25 Sep 2026
Command R+ (04-2024)1262—77554IndependentArena25 Sep 2026
Claude 3 Haiku1262—117701IndependentArena25 Sep 2026
Gemini 1.5 Flash-8B1259—35558IndependentArena25 Sep 2026
Phi-41256—24126IndependentArena25 Sep 2026
OLMo 2 32B Instruct1252—3334IndependentArena25 Sep 2026
Command R (08-2024)1250—10140IndependentArena25 Sep 2026
Mistral Large 1.01243—62436IndependentArena25 Sep 2026
Jamba 1.5 Mini1240—8858IndependentArena25 Sep 2026
Ministral 8B1238—4781IndependentArena25 Sep 2026
Qwen1.5-110B-Chat1234—26195IndependentArena25 Sep 2026
Qwen1.5-72B-Chat1234—39302IndependentArena25 Sep 2026
Mixtral 8x22B1230—51416IndependentArena25 Sep 2026
Command R (03-2024)1227—54036IndependentArena25 Sep 2026
GPT-3.5 Turbo1226—66207IndependentArena25 Sep 2026
Gemini 1.0 Pro1224—6390IndependentArena25 Sep 2026
Aya Expanse 8B1223—9818IndependentArena25 Sep 2026
Llama 3.1 Tulu 3 8B1220—2896IndependentArena25 Sep 2026
Yi-1.5-34B-Chat1213—24146IndependentArena25 Sep 2026
Llama 3.1 8B1211—49605IndependentArena25 Sep 2026
Granite 3.1 8B Instruct1208—3090IndependentArena25 Sep 2026
GPT-3.5 Turbo1204—16619IndependentArena25 Sep 2026
Qwen1.5-32B-Chat1204—21741IndependentArena25 Sep 2026
Gemma 2 2B1200—46616IndependentArena25 Sep 2026
Mixtral 8x7B1197—73503IndependentArena25 Sep 2026
Qwen1.5-14B-Chat1191—17839IndependentArena25 Sep 2026
InternLM2.5-20B-Chat1191—9901IndependentArena25 Sep 2026
DeepSeek LLM 67B Chat1185—4932IndependentArena25 Sep 2026
Yi-34B-Chat1184—15483IndependentArena25 Sep 2026
Granite 3.0 8B Instruct1183—6638IndependentArena25 Sep 2026
Gemma 1.1 7B1183—23893IndependentArena25 Sep 2026
Snowflake Arctic Instruct1180—32832IndependentArena25 Sep 2026
Granite 3.1 2B Instruct1179—3188IndependentArena25 Sep 2026
Llama 3.2 3B1167—7936IndependentArena25 Sep 2026
Nous Hermes 2 Mixtral 8x7B DPO1164—3777IndependentArena25 Sep 2026
Granite 3.0 2B Instruct1157—6837IndependentArena25 Sep 2026
QwQ-32B-Preview1154—3231IndependentArena25 Sep 2026
SOLAR-10.7B-Instruct-v1.01152—4155IndependentArena25 Sep 2026
Mistral 7B v0.21149—19402IndependentArena25 Sep 2026
Falcon-180B Chat1148—1295IndependentArena25 Sep 2026
Qwen1.5-7B-Chat1144—4737IndependentArena25 Sep 2026
Qwen-14B-Chat1139—4964IndependentArena25 Sep 2026
Gemma 7B1138—8925IndependentArena25 Sep 2026
Phi-3-mini1130—20685IndependentArena25 Sep 2026
Gemma 1.1 2B1117—10854IndependentArena25 Sep 2026
Llama 3.2 1B1111—8045IndependentArena25 Sep 2026
Gemma 2B1094—4780IndependentArena25 Sep 2026
Qwen1.5-4B-Chat1091—7597IndependentArena25 Sep 2026
ChatGLM3-6B1057—4658IndependentArena25 Sep 2026
ChatGLM2-6B1025—2658IndependentArena25 Sep 2026
ChatGLM-6B996—4914IndependentArena25 Sep 2026
Dolly 2.0 (3B, 7B, 12B)982—3412IndependentArena25 Sep 2026
StableLM-Alpha 7B953—3287IndependentArena25 Sep 2026
  • Arena (arena.ai), lmarena-ai/leaderboard-dataset, CC BY 4.0.

Sources