Noometry

Model comparison

Qwen1.5-72B vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Qwen1.5-72B scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.8 Max leads 61.7 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 28.8% for Qwen1.5-72B and 92.7% for Qwen3.8 Max.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

Qwen1.5-72BQwen3.8 Max
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.856.8
Released2024-02-042026-08-02
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked2239

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

Category by category

Coding Qwen3.8 Max leads

Qwen1.5-72B: 31.9 (#277), Qwen3.8 Max: 53.5 (#29)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Coding11651502
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%
BigCodeBench Instruct33.2%—
BigCodeBench Complete40.3%—
HumanEval+59.1%—
MBPP+61.6%—

Agentic & Tool Use Not comparable

Qwen1.5-72B: —, Qwen3.8 Max: 45.4 (#14)

BenchmarkQwen1.5-72BQwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Qwen3.8 Max leads

Qwen1.5-72B: 22.2 (#203), Qwen3.8 Max: 54.4 (#26)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Hard Prompts11481496
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
Mystery Game Puzzles—38%
DTBench—92%
LMCA—46.2%
Epoch Capabilities Index—156.41

Math Qwen3.8 Max leads

Qwen1.5-72B: 33.2 (#205), Qwen3.8 Max: 73.2 (#20)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Math11641499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—58%

Knowledge Qwen3.8 Max leads

Qwen1.5-72B: 11.5 (#300), Qwen3.8 Max: 61.7 (#27)

BenchmarkQwen1.5-72BQwen3.8 Max
GPQA Diamond28.8%92.7%
LMArena Expert11361507
SimpleQA Verified—47.3%

Multimodal Not comparable

Qwen1.5-72B: —, Qwen3.8 Max: 37.2 (#75)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Qwen3.8 Max leads

Qwen1.5-72B: 33.2 (#253), Qwen3.8 Max: 56.7 (#18)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Non-English11351472
LMArena Chinese11861538
LMArena French11591503
LMArena German10841483
LMArena Japanese10611467
LMArena Korean10501461
LMArena Russian11041481
LMArena Spanish11101492

Instruction Following Qwen3.8 Max leads

Qwen1.5-72B: 59.3 (#256), Qwen3.8 Max: 77.6 (#17)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Instruction Following11411479

Long Context Qwen3.8 Max leads

Qwen1.5-72B: 35.1 (#243), Qwen3.8 Max: 45.6 (#31)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Longer Query11571489

Writing & Preference Qwen3.8 Max leads

Qwen1.5-72B: 37.3 (#258), Qwen3.8 Max: 67.1 (#30)

BenchmarkQwen1.5-72BQwen3.8 Max
LMArena Text11661483
LMArena Creative Writing11371479
LMArena Multi-Turn11601489

Frequently asked questions

Is Qwen1.5-72B better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.8 on the Noometry Index.

Is Qwen1.5-72B or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 31.9 in the Noometry coding category.

How many benchmarks do Qwen1.5-72B and Qwen3.8 Max share?

18 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper