Skip to main content
Evaluation sources/Arena Text Overall
ParticipatingHuman preference & composite

Arena Text Overall

LMArena · Public model evaluation results from Arena Text Overall.

Official evaluation
Source description

This source measures concrete delivery performance in Human preference & composite; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Gemini 4 Carbon1538.276819275.62026-11-09
Gemini 4 Argon1528.5769991373.82026-10-28
Claude Opus 5.51515.7998278271.52026-10-28
Claude Fable 5.11513.8339203771.22026-10-28
Claude Opus 51507.9090505770.12026-10-28
Claude Opus 4.61501.7236438468.92026-10-28
Muse Wonder1500.9554786668.82026-10-15
Muse Wonder1500.9554786668.82026-10-15
Muse Wonder1499.1665529168.52026-10-28
Gemini 3.8 Flash1498.4923216468.42026-10-28
Claude Fable 51491.561124567.12026-10-28
MiMo V2.6 Pro1491.3511193467.12026-10-28
Muse Spark 1.31490.6255540366.92026-10-28
Claude Opus 4.71489.719561166.82026-10-28
Qwen3.8 Max1483.2905770765.62026-10-28
Muse Spark 1.21482.6647890565.52026-10-28
Gemini 3.1 Pro Preview1480.1061552965.02026-10-28
Gemini 3.6 Flash1479.7907457564.92026-10-28
Muse Spark 1.11478.2815890864.72026-10-28
Kimi K31475.6886282164.22026-10-28
GLM 5.31473.77570563.92026-10-28
GLM-5.3 Flash1473.0371705163.72026-10-28
Claude Sonnet 5.51472.8510730863.72026-10-28
GPT-5.51471.5686765663.42026-10-28
GLM-5.3 Flash1470.5296626563.32026-10-15
GLM-5.3 Flash1470.5296626563.32026-10-15
GLM-5.21469.6433726163.12026-10-28
GPT-5.41469.0796271563.02026-10-28
DeepSeek V4.1 Flash1464.5070280962.22026-10-28
MiMo-V2.5-Pro1464.2246168562.12026-10-28
DeepSeek V4.1 Flash1462.8474205261.92026-10-15
GLM-5.11462.8155878461.92026-10-28
Claude Opus 4.81461.2950585161.62026-10-28
Claude Sonnet 4.61457.7072065860.92026-10-28
Gemini 2.5 Pro1457.7010209660.92026-10-28
GPT-5.6 Sol1457.2397494960.82026-10-28
Kimi K2.61455.5569844460.52026-10-28
MiMo V2.6 Flash1455.2141256160.52026-10-15
MiMo V2.6 Flash1455.2141256160.52026-10-15
Qwen3.7 Plus1454.5576780160.32026-10-28
MiMo V2.6 Flash1451.2183606259.72026-10-28
DeepSeek V4 Pro1451.127948959.72026-10-28
Claude Opus 4.51450.8975320259.72026-10-28
GPT-5.6 Terra1448.3042907359.22026-10-28
Grok 4.51447.6409447459.12026-10-28
Qwen3.6 Max Preview1446.7444158158.92026-10-28
GLM-51445.8732815858.82026-10-28
GPT-6.1 Sol1445.5545772758.72026-10-28
Kimi K2.51444.9047566358.62026-10-28
Step 5 Preview1442.7188262758.22026-10-28
Claude Sonnet 51442.6894798758.22026-10-28
Inkling1442.6633757358.22026-10-28
GPT-6 Astra1441.1545927357.92026-10-28
GLM-4.61440.0559458757.72026-10-28
Hy31439.0652001157.52026-10-28
Claude Sonnet 4.51438.5105346557.42026-10-28
GLM-5V-Turbo1437.7206378257.32026-10-28
Qwen3.5 397B-A17B1437.55338157.22026-10-28
Qwen3.6 Plus1436.3188743957.02026-10-28
MiMo-V2-Pro1436.0772924857.02026-10-28
Gemini 3.5 Flash Lite1435.4764958756.92026-10-28
GLM-4.71435.4336269756.92026-10-28
DeepSeek V4 Flash1431.8349064456.22026-10-28
MiniMax-M31431.2697157956.12026-10-28
GPT-5.6 Luna1431.0486342656.12026-10-28
Mistral Large 41430.0660290555.92026-10-28
GLM-4.51430.0002251855.92026-10-28
Grok 4.61428.5262259755.62026-10-28
Mistral Large 31428.2816908655.62026-10-28
MiMo-V2.51427.8201300255.52026-10-28
R1 05281427.7121292655.52026-10-28
DeepSeek V3.2 Exp1424.9838844155.02026-10-28
DeepSeek V3.21424.4339762954.92026-10-28
MiMo-V2-Omni1423.110648654.62026-10-28
DeepSeek V3.2 Exp1422.1755624154.42026-10-15
Qwen3 VL 235B A22B Instruct1420.0383462854.12026-10-28
DeepSeek V3.11419.5132125354.02026-10-28
GPT-5.5 Instant1419.2072967353.92026-10-28
Qwen3 235B A22B Instruct 25071419.1699403553.92026-10-28
DeepSeek V3.1 Terminus1419.1398329453.92026-10-28
Qwen3.5 122B-A10B1417.5094212753.62026-10-28
DeepSeek V3.1 Terminus1417.1045316553.52026-10-15
Qwen3-Next 80B-A3B Instruct1417.010872953.52026-10-28
Gemini 2.5 Flash1416.9101762753.52026-10-28
GPT-5.21416.2542606853.42026-10-28
Gemini 3.1 Flash Lite Preview1415.789761853.32026-10-28
Qwen3 235B A22B Thinking 25071415.285013853.22026-10-28
Inkling Small1414.3220659253.02026-10-28
Qwen3 Max1412.9329427152.82026-10-15
GPT-5.4 mini1411.5822872952.52026-10-28
o31409.8213257652.22026-10-15
Qwen3.5 27B1408.9868172352.02026-10-28
GPT-51406.1535729951.52026-10-28
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP41404.9717731351.32026-10-28
MiniMax-M2.71404.7893350951.32026-10-28
Step 3.5 Flash1402.7532546350.92026-10-28
Hy3 preview1401.1747117950.62026-10-28
Claude Haiku 5.51400.8832528650.62026-10-28
Qwen3 VL 235B A22B Thinking1400.4905345750.52026-10-28
Grok 4.71398.104358250.12026-10-28
GPT-6 Sol1397.4041561949.92026-10-28
Qwen3.5-Flash1397.0918696749.92026-10-28
Grok 4.31396.8750353849.82026-10-28
Claude Haiku 4.51396.8738757649.82026-10-28
MiMo-V2-Flash1394.5572637149.42026-10-28
Qwen3.5 35B-A3B1394.5404038249.42026-10-28
GPT-6 Luna1389.1534001248.42026-10-28
Qwen3 30B A3B Instruct 25071383.7771810547.42026-10-28
GLM-4.5-Air1383.6899892447.42026-10-28
Nemotron 3 Super 120B A12B1377.3797297346.32026-10-28
GLM-4.6V1376.4801975246.12026-10-28
DeepSeek V3 03241374.6123489845.82026-10-28
GPT-5 mini1373.2050491245.52026-10-28
DeepSeek-R11372.6538489245.42026-10-28
Qwen3-Next 80B-A3B (Thinking)1368.0643809144.62026-10-28
Qwen3 235B-A22B1366.2309120544.22026-10-28
gpt-oss-120b1365.4559711444.12026-10-28
Nova 2 Lite1361.8256109543.42026-10-15
MiniMax-M2.51359.1187658942.92026-10-28
Gemma 3 27B1357.7160204942.72026-10-28
Qwen3-Coder 480B-A35B Instruct1356.5912537142.52026-10-28
Mercury 21354.790519342.22026-10-28
o4-mini1353.294550341.92026-10-15
GLM-4.7-Flash1350.7560835141.42026-10-28
MiniMax M11342.6257915239.92026-10-28
Trinity Large Thinking1340.2823977339.52026-10-28
MiniMax-M21340.0940766539.52026-10-28
Qwen3 32B1340.0649591839.52026-10-28
Llama 3.3 Nemotron Super 49B v1.51338.1216533939.12026-10-28
Llama 3.3 Nemotron Super 49B v1.51338.0469346339.12026-10-15
o3 Mini High1336.5546894938.82026-10-28
Gemma 3 12B1334.1942341638.42026-10-28
GLM-4.5V1332.6347411238.12026-10-28
Command A1330.8998818537.82026-10-28
Qwen Plus1326.3728174837.02026-10-15
GPT-5 nano1319.8944873535.82026-10-28
o3-mini1319.4064542235.72026-10-28
Qwen3 30B A3B1316.9573186935.32026-10-28
Llama 3.3 Nemotron Super 49B v11308.3555186533.72026-10-28
Gemma 3n 4B1305.5909954533.22026-10-28
Olmo 3 32B Think1299.335627232.02026-10-28
Gemma 3 4B1290.7768383830.52026-10-28
Granite 4.1 8B1290.5286748430.42026-10-28
gpt-oss-20b1287.3095111129.82026-10-28
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 41216.6603026317.02026-10-28
Command R1187.335411611.62026-10-28
Llama 3.1 8B Instruct1186.5545901911.52026-10-28
Llama 3.2 1B Instruct1054.609991470.02026-10-28
Llama 3.2 3B Instruct1109.509627640.02026-10-28

Frequently asked questions