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)
$1.60/1M
Output Price (Auto)
$6.39/1M
Cache Read (Auto)
$0.80/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1373.8
Overall Rank
#176 / 395
Votes
32,418
Confidence Interval
1369.7 - 1377.9
Category Scores
Coding
#192 / 390
5,076 votes
1402.2
Math
#184 / 379
3,299 votes
1362.8
Longer Query
#169 / 373
4,523 votes
1384.9
Creative Writing
#158 / 393
4,994 votes
1353.2
Instruction Following
#182 / 395
10,938 votes
1357.0
Hard Prompts
#181 / 395
9,618 votes
1385.1
Additional Categories22
French
#136 / 276
343 votes
1411.8
Japanese
#146 / 261
727 votes
1309.4
German
#157 / 296
781 votes
1354.0
Spanish
#158 / 277
268 votes
1374.0
Korean
#160 / 265
465 votes
1313.6
Polish
#160 / 219
848 votes
1359.1
Industry Writing And Literature And Language
#165 / 394
8,174 votes
1362.2
Russian
#170 / 359
2,981 votes
1367.7
Industry Legal And Government
#171 / 368
1,856 votes
1388.4
Non English
#171 / 395
14,251 votes
1360.5
Industry Entertainment And Sports And Media
#172 / 393
5,968 votes
1339.6
Exclude Ties
#173 / 395
21,826 votes
1348.9
Chinese
#174 / 367
2,074 votes
1396.9
Industry Life And Physical And Social Science
#174 / 393
5,664 votes
1390.2
Industry Medicine And Healthcare
#174 / 363
1,588 votes
1393.6
Multi Turn
#175 / 393
4,815 votes
1373.2
Industry Business And Management And Financial Operations
#179 / 388
3,657 votes
1368.5
Industry Mathematical
#181 / 374
2,940 votes
1366.8
English
#185 / 395
18,167 votes
1382.3
Expert
#188 / 345
1,680 votes
1368.1
Industry Software And It Services
#191 / 395
8,534 votes
1397.6
Hard Prompts English
#195 / 393
5,690 votes
1386.9
Published 2026-08-27 · Matched as qwen2.5-max
LMArena DatasetProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Qwen 2.5 Max with similar models from the same provider or model family.
Qwen3.8 2.4T A95B (Max)
qwen/qwen3.8-2.4t-a95bThis is the same underlying model as Qwen3.8 Max, exposed under its architecture-based 2.4T A95B name for easier discovery. It uses the identical routing, pricing, capabilities, and non-thinking mode.
Qwen3 Max
qwen/qwen3-maxQwen3 Max. The latest Qwen 3 model (5 september 2025). Higher accuracy in coding and science, better instruction following, and optimized for tool calling.
Qwen: QvQ Max
qvq-maxQvQ Max is the top model of the Qwen series. QvQ Max is capable of thinking and reasoning, can achieve significantly enhanced performance especially on hard problems.
Qwen 3.8 27B Fable
qwen/qwen3.8-27b-fableQwen 3.8 27B Fable is an open-weight multimodal creative finetune for expressive dialogue, long-form storytelling, character work, and roleplay.
Qwen 3.8 27B Uncensored Thinking
qwen/qwen3.8-27b-uncensored:thinkingQwen 3.8 27B Uncensored with thinking enabled for more deliberate creative work, coding, multimodal analysis, tool use, and long-context problem solving.
Qwen 3.6 35B A3B Uncensored Thinking
qwen/qwen3.6-35b-a3b-uncensored:thinkingQwen 3.6 35B A3B Uncensored with thinking enabled for more deliberate coding, multimodal analysis, tool use, and complex chat tasks.