Noometry

Model comparison

Gemma 2 27B vs GLM-5.2

GLM-5.2 is the stronger model overall, scoring 51.1 to 29.4 on the Noometry Index. Gemma 2 27B costs 3.3× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.

Last verified . 22 shared benchmarks.

Gemma 2 27B Google

29.4

Rank #312 Confirmed

GLM-5.2 Z.ai (Zhipu)

51.1

Rank #44 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.2 leads 55.7 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 86.4% for GLM-5.2.
  • Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
  • GLM-5.2 accepts more context: 1M tokens versus 8K.

Side by side

Gemma 2 27BGLM-5.2
ProviderGoogleZ.ai (Zhipu)
Noometry Index29.451.1
Released2024-06-242026-06-13
WeightsOpenOpen
Context window8K1M
Max output2K131K
Input $ / M tokens$0.65$1.40
Output $ / M tokens$0.65$4.40
Results tracked3451

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

Category by category

Coding GLM-5.2 leads

Gemma 2 27B: 34.1 (#246), GLM-5.2: 51.3 (#41)

BenchmarkGemma 2 27BGLM-5.2
LMArena Coding12111485
SWE-bench Verified—78.7%
DeepSWE—43.8%
FrontierCode—24.5%
LMArena WebDev—1603
SciCode—50.5%
WeirdML—70.1%
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
BigCodeBench Complete52.5%—
ALE-Bench—1,047

Agentic & Tool Use Not comparable

Gemma 2 27B: —, GLM-5.2: 32.4 (#63)

BenchmarkGemma 2 27BGLM-5.2
APEX-Agents—45.2%
τ²-bench Banking—37.1%
PostTrainBench—31.7%
GBAEval—0%
Vending-Bench 2—8,314

Reasoning GLM-5.2 leads

Gemma 2 27B: 15.3 (#315), GLM-5.2: 42.3 (#52)

BenchmarkGemma 2 27BGLM-5.2
LMArena Hard Prompts11981480
DTBench48%93.6%
LMCA7.1%45.8%
Epoch Capabilities Index122.08151.78
ARC-AGI-2—22.8%
SimpleBench—58.8%
Kagi LLM Benchmark—62.6%
NYT Connections (extended)—74.3%
ARC-AGI-1—77%
CritPt—20.9%
Chess Puzzles—21%
EBR-Bench—9.5%
LiveBench Reasoning28.1%—
Mystery Game Puzzles—19%
LiveBench Data Analysis47.9%—
Surface Evolver Bench—55.6%
LiveBench38.2%—

Math GLM-5.2 leads

Gemma 2 27B: 10.7 (#311), GLM-5.2: 55.7 (#43)

BenchmarkGemma 2 27BGLM-5.2
OTIS Mock AIME 2024-20251.4%86.4%
LMArena Math12121482
FrontierMath (Tiers 1-3)—59.2%
FrontierMath Tier 4—29.3%
MathArena Final-Answer Competitions—67.6%
ProofBench—35%
LiveBench Math26.5%—
MATH Level 527.9%—

Knowledge GLM-5.2 leads

Gemma 2 27B: 19.0 (#280), GLM-5.2: 57.1 (#40)

BenchmarkGemma 2 27BGLM-5.2
GPQA Diamond36.5%91.9%
LMArena Expert11721486
SimpleQA Verified—34.2%
Confabulations27.1%—
MMLU75.7%—

Multilingual GLM-5.2 leads

Gemma 2 27B: 38.6 (#226), GLM-5.2: 55.8 (#26)

BenchmarkGemma 2 27BGLM-5.2
LMArena Non-English12171459
LMArena Chinese12211519
LMArena French12471479
LMArena German12091468
LMArena Japanese11751451
LMArena Korean11741445
LMArena Russian12341466
LMArena Spanish12281477

Instruction Following GLM-5.2 leads

Gemma 2 27B: 60.5 (#249), GLM-5.2: 76.9 (#34)

BenchmarkGemma 2 27BGLM-5.2
LMArena Instruction Following12061465
LiveBench Instruction Following58.1%—

Long Context GLM-5.2 leads

Gemma 2 27B: 37.3 (#218), GLM-5.2: 45.3 (#43)

BenchmarkGemma 2 27BGLM-5.2
LMArena Longer Query12311479

Writing & Preference GLM-5.2 leads

Gemma 2 27B: 44.2 (#225), GLM-5.2: 70.4 (#21)

BenchmarkGemma 2 27BGLM-5.2
LMArena Text12311470
LMArena Creative Writing12411462
LMArena Multi-Turn12241469
EQ-Bench Creative Writing—1757
EQ-Bench 4—1222
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than GLM-5.2?

GLM-5.2 is the stronger model overall, scoring 51.1 to 29.4 on the Noometry Index. Gemma 2 27B costs 3.3× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.

Which is cheaper, Gemma 2 27B or GLM-5.2?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.

Is Gemma 2 27B or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

GLM-5.2 does, with 1M tokens against 8K.

How many benchmarks do Gemma 2 27B and GLM-5.2 share?

22 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and GLM-5.2 has 51.

Related comparisons

Go deeper