Noometry

Alibaba (Qwen), proprietary

Qwen Max

Qwen Max by Alibaba (Qwen) ranks 230th of 354 ranked models on the Noometry Index as of October 2026, with a score of 34.7. Its strongest category is reasoning, where it ranks 151st. API pricing starts at $1.60 per million input tokens and $6.40 per million output tokens, with a 33K-token context window.

Last verified

Noometry rank
#230 of 354
Index score
34.7
Evidence
Confirmed 23 results
Provider
Alibaba (Qwen)
Released
April 3, 2024
Weights
Proprietary
Reasoning
No
Context window
33K
Max output
8K
Input price
$1.60 / M
Output price
$6.40 / M
Blended price
$2.80 / M
Output speed
Not measured
Value
#176 of 219
Knowledge cutoff
April 2024
Input
text

Category scores

Each category score combines every public result we have in that category.

  1. Coding 30.7
  2. Reasoning 25.1
  3. Math 22.3
  4. Knowledge 30.3
  5. Multilingual 41.8
  6. Instruction Following 66.5
  7. Long Context 39.4
  8. Writing & Preference 47.8
CategoryScoreRankResults
Coding30.7#2922
Reasoning25.1#1511
Math22.3#2763
Knowledge30.3#2282
Multilingual41.8#2021
Instruction Following66.5#2081
Long Context39.4#1802
Writing & Preference47.8#2053

Strengths and weaknesses

Categories where Qwen Max places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Reasoning25.1+1.5#151 of 350, top 44%
Long Context39.4−1.5#180 of 296, top 61%
Writing & Preference47.8−6.0#205 of 312, top 66%

Weakest categories

CategoryScorevs medianRank
Coding30.7−8.0#292 of 340, top 86%
Math22.3−14.3#276 of 327, top 85%
Knowledge30.3−7.0#228 of 314, top 73%

Closest competitors

The models ranked just above and below Qwen Max. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
DeepSeek-R1-Distill-Qwen-32B#22635.5——Compare
Magistral Medium#22735.2$2.750Compare
Gemini 2.0 Flash (Feb 2025)#22835.1—92Compare
C4ai Aya Expanse 8b#22934.9——Compare
Claude 3.5 Sonnet#23134.6——Compare
Qwen3 Coder Next#23234.3$0.29—Compare
Devstral Small 2505#23334.3$0.1588Compare
Qwen1.5-110B#23434.2——Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
Aider Polyglot21.8%#34 of 44, top 78%Epoch AI
LMArena Coding1288#206 of 294, top 71%LMArena2026-10-08

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1269#206 of 297, top 70%LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
OTIS Mock AIME 2024-202516.1%#130 of 173, top 76%Epoch AI2025-04-01
LMArena Math1275#194 of 285, top 69%LMArena2026-10-08
MATH Level 567.2%#33 of 79, top 42%Epoch AI2025-04-01
FrontierMath (Feb 2025 set)1%#60 of 68, top 89%Epoch AI2025-04-02

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond56.1%#118 of 186, top 64%Epoch AI2025-04-01
LMArena Expert1248#197 of 273, top 73%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1263#202 of 297, top 69%LMArena2026-10-08
LMArena Chinese1254#205 of 285, top 72%LMArena2026-10-08
LMArena French1330#152 of 223, top 69%LMArena2026-10-08
LMArena German1254#175 of 231, top 76%LMArena2026-10-08
LMArena Japanese1205#159 of 211, top 76%LMArena2026-10-08
LMArena Korean1142#181 of 213, top 85%LMArena2026-10-08
LMArena Russian1274#194 of 283, top 69%LMArena2026-10-08
LMArena Spanish1290#164 of 226, top 73%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1262#201 of 298, top 68%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
Fiction.LiveBench66.7%#22 of 47, top 47%Epoch AI
LMArena Longer Query1288#199 of 291, top 69%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1282#208 of 297, top 71%LMArena2026-10-08
LMArena Creative Writing1248#208 of 295, top 71%LMArena2026-10-08
LMArena Multi-Turn1277#203 of 295, top 69%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
alibaba$1.60$6.40—2026-10-10
fireworks$2$6$0.252026-10-10

All Alibaba (Qwen) API prices → Estimate your cost →

Compare Qwen Max

Other Alibaba (Qwen) models

Frequently asked questions

How good is Qwen Max?

Qwen Max by Alibaba (Qwen) ranks 230th of 354 ranked models on the Noometry Index as of October 2026, with a score of 34.7. Its strongest category is reasoning, where it ranks 151st. API pricing starts at $1.60 per million input tokens and $6.40 per million output tokens, with a 33K-token context window.

How much does Qwen Max cost?

Qwen Max costs $1.60 per million input tokens and $6.40 per million output tokens on Alibaba (Qwen)'s own API.

What is Qwen Max's context window?

Qwen Max accepts up to 33K tokens of input and can write up to 8K tokens in one response.

Is Qwen Max open source?

No. Qwen Max is proprietary and available only through Alibaba (Qwen)'s API and partner platforms.

What are Qwen Max's strengths and weaknesses?

Relative to other ranked models, Qwen Max places best in reasoning, long context, writing & preference and lowest in coding, math, knowledge.

What is Qwen Max best at?

Its best category is reasoning, where it ranks 151st on Noometry.