Noometry

Model comparison

Gemma 4 31B IT vs GLM-4.5

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and GLM-4.5 in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Gemma 4 31B IT leads 44.2 to 38.2.
  • The biggest single-benchmark swing is WeirdML: 52.3% for Gemma 4 31B IT and 40.6% for GLM-4.5.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
  • Gemma 4 31B IT accepts more context: 262K tokens versus 131K.

Side by side

Gemma 4 31B ITGLM-4.5
ProviderGoogleZ.ai (Zhipu)
Noometry Index43.542.0
Released2026-04-022025-07-27
WeightsOpenOpen
Context window262K131K
Max output33K98K
Input $ / M tokens$0.09$0.60
Output $ / M tokens$0.34$2.20
Results tracked3527

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

Category by category

Coding Too close to call

Gemma 4 31B IT: 42.3 (#108), GLM-4.5: 41.4 (#125)

BenchmarkGemma 4 31B ITGLM-4.5
WeirdML52.3%40.6%
LMArena Coding14591434
ALE-Bench925.5344.82
SWE-bench Verified (bash only)—54.2%
LMArena WebDev1366—
SciCode43.4%—
AlgoTune—1.52

Reasoning GLM-4.5 leads

Gemma 4 31B IT: 27.2 (#122), GLM-4.5: 28.6 (#100)

BenchmarkGemma 4 31B ITGLM-4.5
Kagi LLM Benchmark63.5%57.9%
LMArena Hard Prompts14481429
NYT Connections (extended)70.6%—
CritPt1.4%—
Chess Puzzles5%—
Thematic Generalization53%—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Gemma 4 31B IT leads

Gemma 4 31B IT: 43.2 (#81), GLM-4.5: 39.0 (#116)

BenchmarkGemma 4 31B ITGLM-4.5
LMArena Math14651427
OTIS Mock AIME 2024-202573.3%—

Knowledge Gemma 4 31B IT leads

Gemma 4 31B IT: 37.9 (#151), GLM-4.5: 35.9 (#179)

BenchmarkGemma 4 31B ITGLM-4.5
LMArena Expert14651433
GPQA Diamond75.8%—
Humanity's Last Exam—8.3%
SimpleQA Verified10.4%—
Confabulations—11.3%
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 4 31B IT: 41.6 (#34), GLM-4.5: —

BenchmarkGemma 4 31B ITGLM-4.5
LMArena Vision1277—
LMArena Document1425—

Multilingual Too close to call

Gemma 4 31B IT: 53.8 (#57), GLM-4.5: 52.8 (#77)

BenchmarkGemma 4 31B ITGLM-4.5
LMArena Non-English14311417
LMArena Chinese14761465
LMArena French14351418
LMArena Russian14601414
LMArena Spanish14441454
LMArena German—1407
LMArena Japanese—1415
LMArena Korean—1380

Instruction Following Gemma 4 31B IT leads

Gemma 4 31B IT: 75.5 (#61), GLM-4.5: 74.1 (#104)

BenchmarkGemma 4 31B ITGLM-4.5
LMArena Instruction Following14331404

Long Context Gemma 4 31B IT leads

Gemma 4 31B IT: 44.2 (#71), GLM-4.5: 38.2 (#201)

BenchmarkGemma 4 31B ITGLM-4.5
LMArena Longer Query14461412
Fiction.LiveBench—58.3%

Writing & Preference Gemma 4 31B IT leads

Gemma 4 31B IT: 60.5 (#96), GLM-4.5: 57.5 (#127)

BenchmarkGemma 4 31B ITGLM-4.5
LMArena Text14431430
LMArena Creative Writing14151395
EQ-Bench Creative Writing13681343
LMArena Multi-Turn14521415
Short-Story Creative Writing—73.4%
EQ-Bench 41120—

Frequently asked questions

Is Gemma 4 31B IT better than GLM-4.5?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.

Which is cheaper, Gemma 4 31B IT or GLM-4.5?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

Is Gemma 4 31B IT or GLM-4.5 better for coding?

They score almost the same on coding (42.3 vs 41.4); test both on your own repository before choosing.

Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 131K.

How many benchmarks do Gemma 4 31B IT and GLM-4.5 share?

18 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GLM-4.5 has 27.

Related comparisons

Go deeper