Noometry

Alibaba (Qwen), proprietary

Qwen3.7 Max

Qwen3.7 Max by Alibaba (Qwen) ranks 42nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 51.5. Its strongest category is multilingual, where it ranks 15th. API pricing starts at $2.50 per million input tokens and $7.50 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#42 of 354
Index score
51.5
Evidence
Confirmed 33 results
Provider
Alibaba (Qwen)
Released
May 19, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1M
Max output
131K
Input price
$2.50 / M
Output price
$7.50 / M
Blended price
$3.75 / M
Output speed
Not measured
Value
#166 of 219
Knowledge cutoff
Unknown
Input
text

Category scores

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

  1. Coding 50.4
  2. Agentic & Tool Use 22.1
  3. Reasoning 49.2
  4. Math 62.4
  5. Knowledge 61.6
  6. Multilingual 56.9
  7. Instruction Following 76.7
  8. Long Context 45.4
  9. Writing & Preference 65.0
CategoryScoreRankResults
Coding50.4#454
Agentic & Tool Use22.1#1351
Reasoning49.2#389
Math62.4#325
Knowledge61.6#283
Multilingual56.9#151
Instruction Following76.7#381
Long Context45.4#401
Writing & Preference65.0#544

Strengths and weaknesses

Categories where Qwen3.7 Max places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Multilingual56.9+9.5#15 of 297, top 6%
Knowledge61.6+24.3#28 of 314, top 9%
Math62.4+25.9#32 of 327, top 10%

Weakest categories

CategoryScorevs medianRank
Agentic & Tool Use22.1−8.3#135 of 154, top 88%
Writing & Preference65.0+11.2#54 of 312, top 18%
Long Context45.4+4.5#40 of 296, top 14%

Closest competitors

The models ranked just above and below Qwen3.7 Max. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
DeepSeek V4.1 Flash#3852.8$0.26—Compare
GPT-5.2 Pro#3952.3$57.75—Compare
Gemini 3 Flash Preview#4052.3$1.13—Compare
GLM-5.3-Flash#4151.8$0.24—Compare
Qwen3.6 Max Preview#4351.5$2.92—Compare
GLM-5.2#4451.1$2.1523Compare
GPT-5#4550.9$3.442Compare
Muse Spark#4650.6——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
SWE-bench Verified77.3%#7 of 32, top 22%Epoch AI2026-06-18
LMArena WebDev1515#43 of 113, top 39%LMArena2026-10-08
SciCode48.8%#47 of 121, top 39%Epoch AI
LMArena Coding1498#22 of 294, top 8%LMArena2026-10-08
ALE-Bench1,189#31 of 105, top 30%Epoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
GBAEval0.4%#20 of 23, top 87%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
SimpleBench70.4%#11 of 77, top 15%Epoch AI
NYT Connections (extended)85.1%#29 of 91, top 32%Lech Mazur benchmarks
CritPt13.4%#40 of 134, top 30%Epoch AI
Chess Puzzles19%#63 of 129, top 49%Epoch AI2026-08-07
EBR-Bench9.5%#20 of 24, top 84%Epoch AI2026-06-25
LMArena Hard Prompts1483#28 of 297, top 10%LMArena2026-10-08
Mystery Game Puzzles32%#25 of 74, top 34%Epoch AI2026-07-28
Mystery Game Puzzles26%noneEpoch AI2026-08-27
DTBench92.3%#28 of 151, top 19%Epoch AI
LMCA44%#37 of 125, top 30%Epoch AI
Epoch Capabilities Index153.68#39 of 213, top 19%Epoch AI2026-05-19

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)64.6%#33 of 81, top 41%Epoch AI2026-06-13
FrontierMath Tier 434.1%#25 of 63, top 40%Epoch AI2026-06-13
OTIS Mock AIME 2024-202595.6%#35 of 173, top 21%Epoch AI2026-08-07
ProofBench26%#44 of 77, top 58%Epoch AI
LMArena Math1490#18 of 285, top 7%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond90.9%#31 of 186, top 17%Epoch AI2026-08-07
SimpleQA Verified55.8%#19 of 77, top 25%Epoch AI2026-08-27
LMArena Expert1488#34 of 273, top 13%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1474#15 of 297, top 6%LMArena2026-10-08
LMArena Chinese1530#14 of 285, top 5%LMArena2026-10-08
LMArena Russian1484#16 of 283, top 6%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1460#34 of 298, top 12%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1482#19 of 291, top 7%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1476#19 of 297, top 7%LMArena2026-10-08
LMArena Creative Writing1449#29 of 295, top 10%LMArena2026-10-08
EQ-Bench 41110#23 of 28, top 83%EQ-Bench
LMArena Multi-Turn1481#18 of 295, top 7%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
alibaba$2.50$7.50$0.502026-10-10
deepinfra$2.50$7.50$0.502026-10-10
openrouter$1.48$4.42$0.292026-10-10
together$1.25$3.75$0.132026-10-10

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

Compare Qwen3.7 Max

Other Alibaba (Qwen) models

Frequently asked questions

How good is Qwen3.7 Max?

Qwen3.7 Max by Alibaba (Qwen) ranks 42nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 51.5. Its strongest category is multilingual, where it ranks 15th. API pricing starts at $2.50 per million input tokens and $7.50 per million output tokens, with a 1M-token context window.

How much does Qwen3.7 Max cost?

Qwen3.7 Max costs $2.50 per million input tokens and $7.50 per million output tokens on Alibaba (Qwen)'s own API, with cached input at $0.50.

What is Qwen3.7 Max's context window?

Qwen3.7 Max accepts up to 1M tokens of input and can write up to 131K tokens in one response.

Is Qwen3.7 Max open source?

No. Qwen3.7 Max is proprietary and available only through Alibaba (Qwen)'s API and partner platforms.

What are Qwen3.7 Max's strengths and weaknesses?

Relative to other ranked models, Qwen3.7 Max places best in multilingual, knowledge, math and lowest in agentic & tool use, writing & preference, long context.

What is Qwen3.7 Max best at?

Its best category is multilingual, where it ranks 15th on Noometry.