跳过主要内容
评测来源/Arena Text Overall
参与排名真人盲选与综合指数

Arena Text Overall

LMArena · Arena Text Overall 的公开模型评测结果。

官方评测
来源说明

该来源测量模型在「真人盲选与综合指数」领域的具体交付表现，原始成绩会和统一能力读数分开展示。

限制: 不同版本、推理设置和测试集可能导致分数变化，请结合数据时间阅读。

使用方式

参与排名的来源会影响能力分；参考、交叉参考和观察来源仅用于对比与核验。

本来源的模型成绩

Gemini 4 Argon1528.5769991374.22026-10-28
Claude Opus 5.51515.7998278271.82026-10-28
Claude Fable 5.11513.8339203771.52026-10-28
Claude Opus 51507.9090505770.42026-10-28
Claude Opus 4.61501.7236438469.32026-10-28
Muse Wonder1500.9554786669.12026-10-15
Muse Wonder1500.9554786669.12026-10-15
Muse Wonder1499.1665529168.82026-10-28
Gemini 3.8 Flash1498.4923216468.72026-10-28
Claude Fable 51491.561124567.42026-10-28
MiMo V2.6 Pro1491.3511193467.42026-10-28
Muse Spark 1.31490.6255540367.22026-10-28
Claude Opus 4.71489.719561167.12026-10-28
Qwen3.8 Max1483.2905770765.92026-10-28
Muse Spark 1.21482.6647890565.82026-10-28
Gemini 3.1 Pro Preview1480.1061552965.32026-10-28
Gemini 3.6 Flash1479.7907457565.22026-10-28
Muse Spark 1.11478.2815890865.02026-10-28
Kimi K31475.6886282164.52026-10-28
GLM 5.31473.77570564.12026-10-28
GLM-5.3 Flash1473.0371705164.02026-10-28
Claude Sonnet 5.51472.8510730864.02026-10-28
GPT-5.51471.5686765663.72026-10-28
GLM-5.3 Flash1470.5296626563.52026-10-15
GLM-5.3 Flash1470.5296626563.52026-10-15
GLM-5.21469.6433726163.42026-10-28
GPT-5.41469.0796271563.32026-10-28
DeepSeek V4.1 Flash1464.5070280962.42026-10-28
MiMo-V2.5-Pro1464.2246168562.42026-10-28
DeepSeek V4.1 Flash1462.8474205262.12026-10-15
GLM-5.11462.8155878462.12026-10-28
Claude Opus 4.81461.2950585161.82026-10-28
Claude Sonnet 4.61457.7072065861.22026-10-28
Gemini 2.5 Pro1457.7010209661.22026-10-28
GPT-5.6 Sol1457.2397494961.12026-10-28
Kimi K2.61455.5569844460.82026-10-28
MiMo V2.6 Flash1455.2141256160.72026-10-15
MiMo V2.6 Flash1455.2141256160.72026-10-15
Qwen3.7 Plus1454.5576780160.62026-10-28
MiMo V2.6 Flash1451.2183606260.02026-10-28
DeepSeek V4 Pro1451.127948960.02026-10-28
Claude Opus 4.51450.8975320259.92026-10-28
GPT-5.6 Terra1448.3042907359.52026-10-28
Grok 4.51447.6409447459.32026-10-28
Qwen3.6 Max Preview1446.7444158159.22026-10-28
GLM-51445.8732815859.02026-10-28
GPT-6.1 Sol1445.5545772758.92026-10-28
Kimi K2.51444.9047566358.82026-10-28
Step 5 Preview1442.7188262758.42026-10-28
Claude Sonnet 51442.6894798758.42026-10-28
Inkling1442.6633757358.42026-10-28
GPT-6 Astra1441.1545927358.12026-10-28
GLM-4.61440.0559458757.92026-10-28
Hy31439.0652001157.82026-10-28
Claude Sonnet 4.51438.5105346557.72026-10-28
GLM-5V-Turbo1437.7206378257.52026-10-28
Qwen3.5 397B-A17B1437.55338157.52026-10-28
Qwen3.6 Plus1436.3188743957.32026-10-28
MiMo-V2-Pro1436.0772924857.22026-10-28
Gemini 3.5 Flash Lite1435.4764958757.12026-10-28
GLM-4.71435.4336269757.12026-10-28
DeepSeek V4 Flash1431.8349064456.42026-10-28
MiniMax-M31431.2697157956.32026-10-28
GPT-5.6 Luna1431.0486342656.32026-10-28
Mistral Large 41430.0660290556.12026-10-28
GLM-4.51430.0002251856.12026-10-28
Grok 4.61428.5262259755.82026-10-28
Mistral Large 31428.2816908655.82026-10-28
MiMo-V2.51427.8201300255.72026-10-28
R1 05281427.7121292655.72026-10-28
DeepSeek V3.2 Exp1424.9838844155.22026-10-28
DeepSeek V3.21424.4339762955.12026-10-28
MiMo-V2-Omni1423.110648654.82026-10-28
DeepSeek V3.2 Exp1422.1755624154.72026-10-15
Qwen3 VL 235B A22B Instruct1420.0383462854.32026-10-28
DeepSeek V3.11419.5132125354.22026-10-28
GPT-5.5 Instant1419.2072967354.12026-10-28
Qwen3 235B A22B Instruct 25071419.1699403554.12026-10-28
DeepSeek V3.1 Terminus1419.1398329454.12026-10-28
Qwen3.5 122B-A10B1417.5094212753.82026-10-28
DeepSeek V3.1 Terminus1417.1045316553.72026-10-15
Qwen3-Next 80B-A3B Instruct1417.010872953.72026-10-28
Gemini 2.5 Flash1416.9101762753.72026-10-28
GPT-5.21416.2542606853.62026-10-28
Gemini 3.1 Flash Lite Preview1415.789761853.52026-10-28
Qwen3 235B A22B Thinking 25071415.285013853.42026-10-28
Inkling Small1414.3220659253.22026-10-28
Qwen3 Max1412.9329427153.02026-10-15
GPT-5.4 mini1411.5822872952.72026-10-28
o31409.8213257652.42026-10-15
Qwen3.5 27B1408.9868172352.22026-10-28
GPT-51406.1535729951.72026-10-28
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP41404.9717731351.52026-10-28
MiniMax-M2.71404.7893350951.52026-10-28
Step 3.5 Flash1402.7532546351.12026-10-28
Hy3 preview1401.1747117950.82026-10-28
Claude Haiku 5.51400.8832528650.72026-10-28
Qwen3 VL 235B A22B Thinking1400.4905345750.72026-10-28
Grok 4.71398.104358250.22026-10-28
GPT-6 Sol1397.4041561950.12026-10-28
Qwen3.5-Flash1397.0918696750.02026-10-28
Grok 4.31396.8750353850.02026-10-28
Claude Haiku 4.51396.8738757650.02026-10-28
MiMo-V2-Flash1394.5572637149.62026-10-28
Qwen3.5 35B-A3B1394.5404038249.62026-10-28
GPT-6 Luna1389.1534001248.62026-10-28
Qwen3 30B A3B Instruct 25071383.7771810547.62026-10-28
GLM-4.5-Air1383.6899892447.62026-10-28
Nemotron 3 Super 120B A12B1377.3797297346.42026-10-28
GLM-4.6V1376.4801975246.32026-10-28
DeepSeek V3 03241374.6123489845.92026-10-28
GPT-5 mini1373.2050491245.72026-10-28
DeepSeek-R11372.6538489245.62026-10-28
Qwen3-Next 80B-A3B (Thinking)1368.0643809144.72026-10-28
Qwen3 235B-A22B1366.2309120544.42026-10-28
gpt-oss-120b1365.4559711444.22026-10-28
Nova 2 Lite1361.8256109543.62026-10-15
MiniMax-M2.51359.1187658943.12026-10-28
Gemma 3 27B1357.7160204942.82026-10-28
Qwen3-Coder 480B-A35B Instruct1356.5912537142.62026-10-28
Mercury 21354.790519342.32026-10-28
o4-mini1353.294550342.02026-10-15
GLM-4.7-Flash1350.7560835141.52026-10-28
MiniMax M11342.6257915240.02026-10-28
Trinity Large Thinking1340.2823977339.62026-10-28
MiniMax-M21340.0940766539.62026-10-28
Qwen3 32B1340.0649591839.62026-10-28
Llama 3.3 Nemotron Super 49B v1.51338.1216533939.22026-10-28
Llama 3.3 Nemotron Super 49B v1.51338.0469346339.22026-10-15
o3 Mini High1336.5546894938.92026-10-28
Gemma 3 12B1334.1942341638.52026-10-28
GLM-4.5V1332.6347411238.22026-10-28
Command A1330.8998818537.92026-10-28
Qwen Plus1326.3728174837.12026-10-15
GPT-5 nano1319.8944873535.92026-10-28
o3-mini1319.4064542235.82026-10-28
Qwen3 30B A3B1316.9573186935.32026-10-28
Llama 3.3 Nemotron Super 49B v11308.3555186533.82026-10-28
Gemma 3n 4B1305.5909954533.22026-10-28
Olmo 3 32B Think1299.335627232.12026-10-28
Gemma 3 4B1290.7768383830.52026-10-28
Granite 4.1 8B1290.5286748430.52026-10-28
gpt-oss-20b1287.3095111129.92026-10-28
Llama 3.1 Nemotron 70B Instruct1282.6318653429.02026-10-28
Llama-3.3-70B-Instruct1274.2339448927.52026-10-28
Qwen2.5 72B Instruct1268.9953893426.52026-10-28
Llama 3.1 70B Instruct1260.8844836925.02026-10-28
Mistral Small 31233.5352919420.02026-10-28
Gemma 2 27B1231.3547818719.62026-10-28
Qwen2.5 Coder 32B Instruct1230.0212940619.42026-10-28
Command R+1228.8749997219.22026-10-28
Aya Expanse 32B1223.9851424818.32026-10-28
Aya Expanse 32B1223.9704295718.32026-10-15
Phi 41216.6603026316.92026-10-28
Command R1187.335411611.52026-10-28
Llama 3.1 8B Instruct1186.5545901911.42026-10-28
Llama 3.2 1B Instruct1054.609991470.02026-10-28
Llama 3.2 3B Instruct1109.509627640.02026-10-28

常见问题