Loading...
Loading...
LMArena Text
Twitter77
Total Models
1316.26
Average Score
1086.00 - 1470.00
Score Range
1
Max Score Achievable
Top 10 Model Performance
Top 10 of 77
Models Using This Benchmark(77)
OpenAI(20 models)
o3
openai
1449.00
GPT-4.5
openai
1434.00
GPT-4.1
openai
1410.00
o1
openai
1397.00
o4 Mini
openai
1396.00
o1 preview
openai
1381.00
GPT-4.1 Mini
openai
1372.00
o3-mini
openai
1364.00
GPT-4o
openai
1341.00
o1 mini
openai
1333.00
GPT-4o
openai
1328.00
GPT-4 Turbo
openai
1320.00
GPT-4.1 Nano
openai
1318.00
GPT-4 Turbo
openai
1312.00
GPT-4o-mini
openai
1312.00
GPT-4 Turbo
openai
1309.00
GPT-4
openai
1278.00
GPT-4
openai
1263.00
GPT-3.5 Turbo
openai
1215.00
GPT-3.5 Turbo
openai
1187.00
Google(18 models)
Gemini 2.5 Pro Preview
google
1470.00
Gemini 2.5 Pro Preview
google
1446.00
Gemini 2.5 Flash Preview
google
1417.00
Gemini 2.5 Flash Preview
google
1405.00
1387.00
Gemini 2.0 Flash
google
1362.00
Gemma 3 27B
google
1359.00
Gemini 1.5 Pro
google
1346.00
Gemma 3 12B
google
1339.00
Gemma 3n E4B
google
1308.00
Gemini 1.5 Flash
google
1307.00
Gemma 3 4B
google
1299.00
Gemma 2 27B
google
1285.00
Gemma 2 9B
google
1258.00
Gemini 1.5 Flash 8B
google
1257.00
Gemma 2 2B
google
1195.00
Gemma 1 7B
google
1126.00
Gemma 1 2B
google
1086.00
Anthropic(9 models)
Claude Opus 4
anthropic
1419.00
Claude Sonnet 4
anthropic
1394.00
Claude 3.7 Sonnet
anthropic
1385.00
Claude 3.5 Sonnet
anthropic
1364.00
Claude 3.5 Sonnet
anthropic
1338.00
Claude 3 Opus
anthropic
1317.00
Claude 3.5 Haiku
anthropic
1312.00
Claude 3 Sonnet
anthropic
1275.00
Claude 3 Haiku
anthropic
1256.00
Cohere(5 models)
Command A
cohere
1344.00
Command R+
cohere
1275.00
Command R+
cohere
1261.00
Command R
cohere
1254.00
Command R
cohere
1226.00
DeepSeek(5 models)
R1
deepseek
1411.00
DeepSeek-V3 0324
deepseek
1396.00
R1
deepseek
1393.00
DeepSeek-V3
deepseek
1355.00
DeepSeek-V2.5
deepseek
1304.00
Meta(5 models)
1312.00
1273.00
1220.00
1211.00
1171.00
Qwen(4 models)
Amazon(3 models)
Nvidia(3 models)
1326.00
1324.00
1294.00
ai21(2 models)
Jamba Large 1.5
ai21
1283.00
Jamba Mini 1.5
ai21
1238.00
xAI(2 models)
Grok 3 Beta
x-ai
1406.00
Grok 3 Mini Beta
x-ai
1355.00
Microsoft(1 model)
Phi 4
microsoft
1255.00