Private AI
Qwen 2.5 Max is the upgraded version of Qwen Max, beating GPT-4o, Deepseek V3 and Claude 3.5 Sonnet in benchmarks.
Added Oct 1, 2024
Context Window
32.0K
Max Output
8.2K
Input Price (Auto)
$1.44/1M
Output Price (Auto)
$5.75/1M
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1374.3
Overall Rank
#142 / 360
Votes
32,623
Confidence Interval
1370.2 - 1378.4
Coding
#157 / 355
5,101 votes
1402.9
Math
#152 / 349
3,306 votes
1364.2
Longer Query
#136 / 338
4,516 votes
1384.1
Creative Writing
#127 / 358
5,000 votes
1354.4
Instruction Following
#149 / 360
10,959 votes
1356.7
Hard Prompts
#147 / 360
9,673 votes
1385.1
French
#107 / 245
328 votes
1411.9
Japanese
#113 / 228
691 votes
1310.2
Spanish
#125 / 248
249 votes
1375.6
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
German
#131 / 270
761 votes
1353.4
Korean
#131 / 240
470 votes
1315.1
Industry Writing And Literature And Language
#132 / 359
8,196 votes
1362.5
Industry Legal And Government
#138 / 333
1,868 votes
1386.5
Russian
#138 / 323
2,808 votes
1365.6
Chinese
#139 / 330
1,950 votes
1397.9
Exclude Ties
#140 / 360
21,983 votes
1349.7
Industry Medicine And Healthcare
#140 / 329
1,600 votes
1394.4
Industry Entertainment And Sports And Media
#141 / 358
5,991 votes
1339.8
Industry Life And Physical And Social Science
#141 / 358
5,699 votes
1389.7
Multi Turn
#141 / 358
4,870 votes
1372.5
Industry Business And Management And Financial Operations
#145 / 353
3,681 votes
1368.8
English
#149 / 360
18,692 votes
1382.4
Industry Mathematical
#149 / 342
2,942 votes
1368.1
Expert
#151 / 309
1,668 votes
1367.2
Industry Software And It Services
#157 / 360
8,629 votes
1397.7
Hard Prompts English
#158 / 359
6,011 votes
1387.8
Published 2026-05-27 · Matched as qwen2.5-max
LMArena Dataset