Noometry

Model comparison

Gemma 2 27B vs GLM-4.5-Air

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemma 2 27B Google

29.4

Rank #312 Confirmed

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemma 2 27B scores higher in 1 category and GLM-4.5-Air in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.5-Air leads 36.2 to 10.7.
  • GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
  • GLM-4.5-Air accepts more context: 131K tokens versus 8K.

Side by side

Gemma 2 27BGLM-4.5-Air
ProviderGoogleZ.ai (Zhipu)
Noometry Index29.438.9
Released2024-06-242025-07-20
WeightsOpenOpen
Context window8K131K
Max output2K98K
Input $ / M tokens$0.65$0.20
Output $ / M tokens$0.65$1.10
Results tracked3427

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

Category by category

Coding Too close to call

Gemma 2 27B: 34.1 (#246), GLM-4.5-Air: 33.3 (#259)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Coding12111397
GSO—2.9%
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
BigCodeBench Complete52.5%—

Reasoning GLM-4.5-Air leads

Gemma 2 27B: 15.3 (#315), GLM-4.5-Air: 24.1 (#166)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Hard Prompts11981379
Kagi LLM Benchmark—43%
LiveBench Reasoning28.1%—
DTBench48%—
LiveBench Data Analysis47.9%—
LMCA7.1%—
Epoch Capabilities Index122.08—
ForecastBench—59.2
LiveBench38.2%—

Math GLM-4.5-Air leads

Gemma 2 27B: 10.7 (#311), GLM-4.5-Air: 36.2 (#170)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Math12121396
OTIS Mock AIME 2024-20251.4%—
Omni-MATH—39.1%
LiveBench Math26.5%—
MATH Level 527.9%—

Knowledge GLM-4.5-Air leads

Gemma 2 27B: 19.0 (#280), GLM-4.5-Air: 35.0 (#191)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Expert11721370
GPQA Diamond36.5%—
Humanity's Last Exam—8.1%
MMLU-Pro—76.2%
Confabulations27.1%—
Vectara Hallucination Rate—9.3%
GPQA (HELM)—59.4%
MMLU75.7%—

Multilingual GLM-4.5-Air leads

Gemma 2 27B: 38.6 (#226), GLM-4.5-Air: 49.1 (#135)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Non-English12171366
LMArena Chinese12211426
LMArena French12471399
LMArena German12091377
LMArena Japanese11751348
LMArena Korean11741308
LMArena Russian12341373
LMArena Spanish12281386

Instruction Following GLM-4.5-Air leads

Gemma 2 27B: 60.5 (#249), GLM-4.5-Air: 69.6 (#171)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Instruction Following12061354
LiveBench Instruction Following58.1%—
IFEval—81.2%

Long Context GLM-4.5-Air leads

Gemma 2 27B: 37.3 (#218), GLM-4.5-Air: 41.6 (#135)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Longer Query12311366

Writing & Preference GLM-4.5-Air leads

Gemma 2 27B: 44.2 (#225), GLM-4.5-Air: 55.9 (#139)

BenchmarkGemma 2 27BGLM-4.5-Air
LMArena Text12311384
LMArena Creative Writing12411343
LMArena Multi-Turn12241371
WildBench—78.9%
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than GLM-4.5-Air?

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.4 on the Noometry Index.

Which is cheaper, Gemma 2 27B or GLM-4.5-Air?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

Is Gemma 2 27B or GLM-4.5-Air better for coding?

They score almost the same on coding (34.1 vs 33.3); test both on your own repository before choosing.

Which has the bigger context window?

GLM-4.5-Air does, with 131K tokens against 8K.

How many benchmarks do Gemma 2 27B and GLM-4.5-Air share?

17 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and GLM-4.5-Air has 27.

Related comparisons

Go deeper