Noometry

Model comparison

Qwen2-72B vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.0 on the Noometry Index.

Last verified . 19 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 30.2.
  • The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 92.7% for Qwen3.8 Max.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Qwen2-72BQwen3.8 Max
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.056.8
Released2024-06-072026-08-02
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked2639

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

Category by category

Coding Qwen3.8 Max leads

Qwen2-72B: 29.1 (#310), Qwen3.8 Max: 53.5 (#29)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Coding11961502
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%
WeirdML11.3%—
BigCodeBench Instruct38.5%—
BigCodeBench Complete54%—

Agentic & Tool Use Qwen3.8 Max leads

Qwen2-72B: 17.0 (#146), Qwen3.8 Max: 45.4 (#14)

BenchmarkQwen2-72BQwen3.8 Max
APEX-Agents—63.3%
TheAgentCompany1.1%—
τ²-bench Banking—55.1%
GDP.pdf—23.2%
METR Time Horizons29.9%—

Reasoning Qwen3.8 Max leads

Qwen2-72B: 23.2 (#181), Qwen3.8 Max: 54.4 (#26)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Hard Prompts11911496
Epoch Capabilities Index125.28156.41
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
Mystery Game Puzzles—38%
DTBench—92%
LMCA—46.2%

Math Qwen3.8 Max leads

Qwen2-72B: 30.2 (#236), Qwen3.8 Max: 73.2 (#20)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Math12351499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—58%
MATH Level 539.1%—

Knowledge Qwen3.8 Max leads

Qwen2-72B: 21.2 (#275), Qwen3.8 Max: 61.7 (#27)

BenchmarkQwen2-72BQwen3.8 Max
GPQA Diamond40.8%92.7%
LMArena Expert11711507
SimpleQA Verified—47.3%
MMLU82.4%—

Multimodal Not comparable

Qwen2-72B: —, Qwen3.8 Max: 37.2 (#75)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Qwen3.8 Max leads

Qwen2-72B: 35.9 (#244), Qwen3.8 Max: 56.7 (#18)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Non-English11761472
LMArena Chinese12401538
LMArena French11701503
LMArena German11511483
LMArena Japanese11111467
LMArena Korean10831461
LMArena Russian11691481
LMArena Spanish11691492

Instruction Following Qwen3.8 Max leads

Qwen2-72B: 61.7 (#241), Qwen3.8 Max: 77.6 (#17)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Instruction Following11811479

Long Context Qwen3.8 Max leads

Qwen2-72B: 36.1 (#235), Qwen3.8 Max: 45.6 (#31)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Longer Query11921489

Writing & Preference Qwen3.8 Max leads

Qwen2-72B: 40.8 (#241), Qwen3.8 Max: 67.1 (#30)

BenchmarkQwen2-72BQwen3.8 Max
LMArena Text12031483
LMArena Creative Writing11811479
LMArena Multi-Turn11961489

Frequently asked questions

Is Qwen2-72B better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.0 on the Noometry Index.

Is Qwen2-72B or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 29.1 in the Noometry coding category.

How many benchmarks do Qwen2-72B and Qwen3.8 Max share?

19 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper