Noometry

Model comparison

Qwen2.5 72B Instruct vs Qwen3.7 Plus

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 31.5 on the Noometry Index.

Last verified . 22 shared benchmarks.

Qwen2.5 72B Instruct Alibaba (Qwen)

31.5

Rank #259 Confirmed

Qwen3.7 Plus Alibaba (Qwen)

45.0

Rank #66 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 1 category and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.7 Plus leads 49.3 to 18.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.1% for Qwen2.5 72B Instruct and 93.3% for Qwen3.7 Plus.
  • Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
  • Qwen3.7 Plus accepts more context: 1M tokens versus 131K.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Qwen2.5 72B InstructQwen3.7 Plus
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index31.545.0
Released2024-092026-06-02
WeightsOpenProprietary
Context window131K1M
Max output8K131K
Input $ / M tokens$1.40$0.40
Output $ / M tokens$5.60$1.60
Results tracked4332

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

Category by category

Coding Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 32.8 (#256), Qwen3.7 Plus: 36.1 (#200)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
LMArena Coding12931473
FrontierCode—10.2%
SciCode—45.5%
WeirdML16%—
BigCodeBench Instruct45.8%—
BigCodeBench Complete55.9%—

Agentic & Tool Use Too close to call

Qwen2.5 72B Instruct: 22.0 (#124), Qwen3.7 Plus: 21.2 (#130)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
OSWorld 2.0—2.8%
TheAgentCompany5.7%—
BALROG16.2%—
METR Time Horizons35.8%—

Reasoning Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 21.4 (#197), Qwen3.7 Plus: 38.4 (#54)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
LMArena Hard Prompts12711460
DTBench62.9%84%
LMCA13.4%37.6%
Epoch Capabilities Index129.01147.39
NYT Connections (extended)—74.8%
CritPt—9.1%
Chess Puzzles—24%
Mystery Game Puzzles—17%
BIG-Bench Hard79.8%—
ForecastBench57.5—
HellaSwag84.8%—
PIQA82.6%—
WinoGrande82.3%—

Math Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 18.1 (#281), Qwen3.7 Plus: 49.3 (#47)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
OTIS Mock AIME 2024-20258.1%93.3%
LMArena Math12831467
FrontierMath (Tiers 1-3)—34.4%
Omni-MATH33%—
MATH Level 563.2%—

Knowledge Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 26.9 (#247), Qwen3.7 Plus: 54.9 (#46)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
GPQA Diamond49.1%87.9%
LMArena Expert12451467
MMLU-Pro63.1%—
Confabulations19.1%—
GPQA (HELM)42.6%—
ARC (AI2) Challenge94.5%—
MMLU85.3%—
TriviaQA71.9%—

Multimodal Not comparable

Qwen2.5 72B Instruct: —, Qwen3.7 Plus: 41.2 (#30)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
LMArena Vision—1281
LMArena Document—1444

Multilingual Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 41.2 (#208), Qwen3.7 Plus: 55.0 (#36)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
LMArena Non-English12521445
LMArena Chinese12721510
LMArena French12791471
LMArena German12341471
LMArena Japanese11801411
LMArena Korean11881416
LMArena Russian12641457
LMArena Spanish12551453

Instruction Following Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 65.7 (#216), Qwen3.7 Plus: 75.9 (#49)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
LMArena Instruction Following12541439
IFEval80.6%—

Long Context Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 38.9 (#183), Qwen3.7 Plus: 44.5 (#61)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
LMArena Longer Query12821454

Writing & Preference Qwen3.7 Plus leads

Qwen2.5 72B Instruct: 46.9 (#210), Qwen3.7 Plus: 64.5 (#54)

BenchmarkQwen2.5 72B InstructQwen3.7 Plus
LMArena Text12691454
LMArena Creative Writing12211439
LMArena Multi-Turn12721459
WildBench80.2%—

Frequently asked questions

Is Qwen2.5 72B Instruct better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 31.5 on the Noometry Index.

Which is cheaper, Qwen2.5 72B Instruct or Qwen3.7 Plus?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

Is Qwen2.5 72B Instruct or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 32.8 in the Noometry coding category.

Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 131K.

How many benchmarks do Qwen2.5 72B Instruct and Qwen3.7 Plus share?

22 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Qwen3.7 Plus has 32.

Related comparisons

Go deeper