Noometry

Model comparison

Qwen2.5 72B Instruct vs Qwen3.7 Flash

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 31.9 on the Noometry Index.

Last verified . 3 shared benchmarks.

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Qwen3.7 Flash Alibaba (Qwen)

39.9

Rank #156 Confirmed

Summary

  • They share 3 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 0 categories and Qwen3.7 Flash in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.7 Flash leads 48.9 to 27.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.1% for Qwen2.5 72B Instruct and 86.7% for Qwen3.7 Flash.
  • Qwen3.7 Flash is cheaper at $0.03 / $0.13 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
  • Qwen3.7 Flash 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 Flash
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index31.939.9
Released2024-092026-07-15
WeightsOpenProprietary
Context window131K1M
Max output8K131K
Input $ / M tokens$1.40$0.03
Output $ / M tokens$5.60$0.13
Results tracked437

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

Category by category

Coding Not comparable

Qwen2.5 72B Instruct: 33.2 (#260), Qwen3.7 Flash: —

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
WeirdML16%—
BigCodeBench Instruct45.8%—
LMArena Coding1292—
BigCodeBench Complete55.9%—

Agentic & Tool Use Not comparable

Qwen2.5 72B Instruct: 22.1 (#133), Qwen3.7 Flash: —

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
TheAgentCompany5.7%—
BALROG16.2%—
METR Time Horizons35.8%—

Reasoning Qwen3.7 Flash leads

Qwen2.5 72B Instruct: 22.3 (#199), Qwen3.7 Flash: 28.2 (#108)

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
Epoch Capabilities Index129144.64
NYT Connections (extended)—43.8%
Chess Puzzles—23%
LMArena Hard Prompts1271—
Mystery Game Puzzles—15%
DTBench62.9%—
LMCA13.4%—
BIG-Bench Hard79.8%—
ForecastBench57.5—
HellaSwag84.8%—
PIQA82.6%—
WinoGrande82.3%—

Math Qwen3.7 Flash leads

Qwen2.5 72B Instruct: 19.3 (#287), Qwen3.7 Flash: 38.3 (#140)

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
OTIS Mock AIME 2024-20258.1%86.7%
FrontierMath (Tiers 1-3)—19.3%
Omni-MATH33%—
LMArena Math1283—
MATH Level 563.2%—

Knowledge Qwen3.7 Flash leads

Qwen2.5 72B Instruct: 27.0 (#253), Qwen3.7 Flash: 48.9 (#75)

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
GPQA Diamond49.1%82.3%
MMLU-Pro63.1%—
Confabulations19.1%—
GPQA (HELM)42.6%—
LMArena Expert1245—
ARC (AI2) Challenge94.5%—
MMLU85.3%—
TriviaQA71.9%—

Multilingual Not comparable

Qwen2.5 72B Instruct: 41.0 (#213), Qwen3.7 Flash: —

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
LMArena Non-English1252—
LMArena Chinese1272—
LMArena French1280—
LMArena German1234—
LMArena Japanese1180—
LMArena Korean1188—
LMArena Russian1264—
LMArena Spanish1256—

Instruction Following Not comparable

Qwen2.5 72B Instruct: 65.5 (#221), Qwen3.7 Flash: —

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
IFEval80.6%—
LMArena Instruction Following1254—

Long Context Not comparable

Qwen2.5 72B Instruct: 38.9 (#188), Qwen3.7 Flash: —

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
LMArena Longer Query1282—

Writing & Preference Not comparable

Qwen2.5 72B Instruct: 46.7 (#215), Qwen3.7 Flash: —

BenchmarkQwen2.5 72B InstructQwen3.7 Flash
LMArena Text1269—
LMArena Creative Writing1221—
WildBench80.2%—
LMArena Multi-Turn1272—

Frequently asked questions

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

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 31.9 on the Noometry Index.

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

Qwen3.7 Flash is cheaper. It lists at $0.03 per million input tokens and $0.13 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

Which has the bigger context window?

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

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

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

Related comparisons

Go deeper