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
1373.9
Overall Rank
#181 / 402
Votes
32,417
Confidence Interval
1369.8 - 1378.0
Category Scores
Coding
#196 / 397
5,076 votes
1402.2
Math
#189 / 384
3,298 votes
1362.8
Longer Query
#173 / 380
4,522 votes
1384.9
Creative Writing
#162 / 400
4,994 votes
1353.2
Instruction Following
#186 / 402
10,937 votes
1356.9
Hard Prompts
#185 / 402
9,618 votes
1385.2
Additional Categories22
French
#141 / 281
343 votes
1411.8
Japanese
#150 / 265
727 votes
1309.4
German
#160 / 299
781 votes
1354.2
Polish
#163 / 222
849 votes
1358.6
Spanish
#163 / 283
268 votes
1374.1
Korean
#164 / 269
465 votes
1313.8
Industry Writing And Literature And Language
#169 / 401
8,174 votes
1362.3
Russian
#173 / 366
2,980 votes
1367.8
Industry Legal And Government
#175 / 375
1,856 votes
1388.4
Industry Entertainment And Sports And Media
#176 / 400
5,968 votes
1339.5
Non English
#176 / 402
14,251 votes
1360.7
Exclude Ties
#177 / 402
21,825 votes
1349.1
Chinese
#178 / 373
2,074 votes
1396.7
Industry Life And Physical And Social Science
#178 / 400
5,665 votes
1390.2
Industry Medicine And Healthcare
#179 / 371
1,589 votes
1393.5
Multi Turn
#179 / 400
4,815 votes
1373.0
Industry Business And Management And Financial Operations
#182 / 395
3,657 votes
1368.6
Industry Mathematical
#186 / 379
2,940 votes
1366.5
English
#189 / 402
18,166 votes
1382.2
Expert
#193 / 352
1,680 votes
1367.6
Industry Software And It Services
#195 / 402
8,533 votes
1397.6
Hard Prompts English
#199 / 400
5,690 votes
1386.7
Published 2026-09-13 · Matched as qwen2.5-max
LMArena DatasetProviders
Provider information for this model’s automatic routing. These routes cannot be selected individually.
Loading provider options…
Related text models
Compare Qwen 2.5 Max with similar models from the same provider or model family.
Qwen3 Max
qwen/qwen3-maxQwen3 Max improves accuracy in coding and science, instruction following, and 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 Cybersecurity
qwen/qwen3.8-27b-cybersecurityQwen 3.8 27B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.
Qwen 3.8 27B Queen
qwen/qwen3.8-27b-queenQwen 3.8 27B Queen is an FP8 open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 524,288-token context window.
Qwen3.8 Max 0902
qwen/qwen3.8-max-0902Qwen3.8 Max 0902 is Alibaba's September 2 checkpoint of its flagship Qwen3.8 Max model for coding, knowledge work, data analysis, and long-running agent workflows. It supports text, image, video, PDF input, selectable thinking, tool calling, structured output, and a near-million-token context window.
Qwen3.8 Max
qwen/qwen3.8-maxQwen3.8 Max is Qwen's 2.4T-parameter flagship model for coding, knowledge work, full-stack development, data analysis, and long-running agent workflows in non-thinking mode. It supports text, image, video, PDF input, tool calling, structured output, and a near-million-token context window.