Noometry

Model comparison

Gemma 4 26B A4B IT vs GLM-4.7

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.

Last verified . 24 shared benchmarks.

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 4 categories and GLM-4.7 in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 38.6.
  • The biggest single-benchmark swing is GPQA Diamond: 73.2% for Gemma 4 26B A4B IT and 83.3% for GLM-4.7.
  • Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
  • Gemma 4 26B A4B IT accepts more context: 262K tokens versus 205K.

Side by side

Gemma 4 26B A4B ITGLM-4.7
ProviderGoogleZ.ai (Zhipu)
Noometry Index43.542.0
Released2026-04-022025-12-22
WeightsOpenOpen
Context window262K205K
Max output33K131K
Input $ / M tokens$0.0675$0.60
Output $ / M tokens$0.23$2.20
Results tracked2836

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

Category by category

Coding GLM-4.7 leads

Gemma 4 26B A4B IT: 39.0 (#164), GLM-4.7: 44.0 (#79)

BenchmarkGemma 4 26B A4B ITGLM-4.7
LMArena WebDev13591435
SciCode40%45.1%
LMArena Coding14471454
ALE-Bench927.17399.48
WeirdML35.2%—

Agentic & Tool Use Not comparable

Gemma 4 26B A4B IT: —, GLM-4.7: 26.5 (#103)

BenchmarkGemma 4 26B A4B ITGLM-4.7
Terminal-Bench—33.4%
Vending-Bench 2—2,377

Reasoning GLM-4.7 leads

Gemma 4 26B A4B IT: 21.8 (#213), GLM-4.7: 24.3 (#164)

BenchmarkGemma 4 26B A4B ITGLM-4.7
CritPt0%1.7%
Chess Puzzles6%6%
LMArena Hard Prompts14391443
Epoch Capabilities Index141.85143.51
SimpleBench—47.7%
DTBench74.9%—
LMCA29.7%—

Math Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 47.6 (#67), GLM-4.7: 38.6 (#135)

BenchmarkGemma 4 26B A4B ITGLM-4.7
OTIS Mock AIME 2024-202582.2%83.3%
LMArena Math14701423
ProofBench—6%
FrontierMath (Feb 2025 set)—2.4%
FrontierMath Tier 4 (v1)—0%

Knowledge GLM-4.7 leads

Gemma 4 26B A4B IT: 45.7 (#85), GLM-4.7: 47.0 (#80)

BenchmarkGemma 4 26B A4B ITGLM-4.7
GPQA Diamond73.2%83.3%
Vectara Hallucination Rate5.2%11.7%
LMArena Expert14471424
SimpleQA Verified—32.2%

Multimodal Not comparable

Gemma 4 26B A4B IT: 40.6 (#46), GLM-4.7: —

BenchmarkGemma 4 26B A4B ITGLM-4.7
LMArena Vision1260—

Multilingual Too close to call

Gemma 4 26B A4B IT: 53.1 (#71), GLM-4.7: 52.8 (#79)

BenchmarkGemma 4 26B A4B ITGLM-4.7
LMArena Non-English14211417
LMArena Chinese14951495
LMArena French14601432
LMArena Russian14341423
LMArena Spanish14171434
LMArena German—1424
LMArena Japanese—1439
LMArena Korean—1399

Instruction Following Too close to call

Gemma 4 26B A4B IT: 74.8 (#82), GLM-4.7: 74.4 (#95)

BenchmarkGemma 4 26B A4B ITGLM-4.7
LMArena Instruction Following14201411

Long Context Too close to call

Gemma 4 26B A4B IT: 43.6 (#91), GLM-4.7: 42.8 (#116)

BenchmarkGemma 4 26B A4B ITGLM-4.7
LMArena Longer Query14281432
CL-bench—15.9%
CL-bench Life—10.9%

Writing & Preference GLM-4.7 leads

Gemma 4 26B A4B IT: 58.6 (#115), GLM-4.7: 60.9 (#93)

BenchmarkGemma 4 26B A4B ITGLM-4.7
LMArena Text14341435
LMArena Creative Writing14021401
EQ-Bench Creative Writing13051413
LMArena Multi-Turn14411446

Frequently asked questions

Is Gemma 4 26B A4B IT better than GLM-4.7?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.

Which is cheaper, Gemma 4 26B A4B IT or GLM-4.7?

Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is Gemma 4 26B A4B IT or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 39.0 in the Noometry coding category.

Which has the bigger context window?

Gemma 4 26B A4B IT does, with 262K tokens against 205K.

How many benchmarks do Gemma 4 26B A4B IT and GLM-4.7 share?

24 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper