Noometry

Model comparison

GLM-4.7-Flash vs Qwen2.5 72B Instruct

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 31.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.4

Rank #175 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.5

Rank #259 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GLM-4.7-Flash scores higher in 7 categories and Qwen2.5 72B Instruct in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7-Flash leads 34.4 to 18.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 8.1% for Qwen2.5 72B Instruct.
  • GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
  • GLM-4.7-Flash accepts more context: 200K tokens versus 131K.

Side by side

GLM-4.7-FlashQwen2.5 72B Instruct
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index38.431.5
Released2026-01-192024-09
WeightsOpenOpen
Context window200K131K
Max output131K8K
Input $ / M tokens$0.06$1.40
Output $ / M tokens$0.40$5.60
Results tracked2143

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

Category by category

Coding GLM-4.7-Flash leads

GLM-4.7-Flash: 40.0 (#133), Qwen2.5 72B Instruct: 32.8 (#256)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
LMArena Coding13831293
WeirdML—16%
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, Qwen2.5 72B Instruct: 22.0 (#124)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
TheAgentCompany—5.7%
BALROG—16.2%
METR Time Horizons—35.8%

Reasoning Qwen2.5 72B Instruct leads

GLM-4.7-Flash: 20.2 (#224), Qwen2.5 72B Instruct: 21.4 (#197)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
LMArena Hard Prompts13561271
Chess Puzzles0%—
DTBench—62.9%
LMCA—13.4%
BIG-Bench Hard—79.8%
Epoch Capabilities Index—129.01
ForecastBench—57.5
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math GLM-4.7-Flash leads

GLM-4.7-Flash: 34.4 (#159), Qwen2.5 72B Instruct: 18.1 (#281)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
OTIS Mock AIME 2024-202558.3%8.1%
LMArena Math13541283
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge GLM-4.7-Flash leads

GLM-4.7-Flash: 35.4 (#177), Qwen2.5 72B Instruct: 26.9 (#247)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
GPQA Diamond60.5%49.1%
LMArena Expert13571245
MMLU-Pro—63.1%
Confabulations—19.1%
Vectara Hallucination Rate9.3%—
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multilingual GLM-4.7-Flash leads

GLM-4.7-Flash: 46.8 (#152), Qwen2.5 72B Instruct: 41.2 (#208)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
LMArena Non-English13311252
LMArena Chinese14031272
LMArena French13321279
LMArena German13361234
LMArena Korean12841188
LMArena Russian13331264
LMArena Spanish13511255
LMArena Japanese—1180

Instruction Following GLM-4.7-Flash leads

GLM-4.7-Flash: 70.3 (#162), Qwen2.5 72B Instruct: 65.7 (#216)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
LMArena Instruction Following13271254
IFEval—80.6%

Long Context GLM-4.7-Flash leads

GLM-4.7-Flash: 40.9 (#143), Qwen2.5 72B Instruct: 38.9 (#183)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
LMArena Longer Query13451282

Writing & Preference Too close to call

GLM-4.7-Flash: 47.7 (#206), Qwen2.5 72B Instruct: 46.9 (#210)

BenchmarkGLM-4.7-FlashQwen2.5 72B Instruct
LMArena Text13511269
LMArena Creative Writing12971221
LMArena Multi-Turn13421272
EQ-Bench Creative Writing1125—
WildBench—80.2%

Frequently asked questions

Is GLM-4.7-Flash better than Qwen2.5 72B Instruct?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 31.5 on the Noometry Index.

Which is cheaper, GLM-4.7-Flash or Qwen2.5 72B Instruct?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

Is GLM-4.7-Flash or Qwen2.5 72B Instruct better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 32.8 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 131K.

How many benchmarks do GLM-4.7-Flash and Qwen2.5 72B Instruct share?

18 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper