Noometry

Model comparison

Gemini 3.1 Pro Preview vs GLM-4.5-Air

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 38.7 on the Noometry Index. GLM-4.5-Air costs 11× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #20 Confirmed

GLM-4.5-Air Z.ai (Zhipu)

38.7

Rank #169 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and GLM-4.5-Air in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 23.3.
  • The biggest single-benchmark swing is Humanity's Last Exam: 46.4% for Gemini 3.1 Pro Preview and 8.1% for GLM-4.5-Air.
  • GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 131K.
  • GLM-4.5-Air has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewGLM-4.5-Air
ProviderGoogleZ.ai (Zhipu)
Noometry Index56.738.7
Released2026-02-192025-07-20
WeightsProprietaryOpen
Context window1.05M131K
Max output66K98K
Input $ / M tokens$2$0.20
Output $ / M tokens$12$1.10
Results tracked7127

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

Category by category

Coding Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 42.7 (#88), GLM-4.5-Air: 34.5 (#225)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
GSO22.6%2.9%
LMArena Coding14831397
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1446—
SciCode58.9%—
WeirdML72.1%—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Not comparable

Gemini 3.1 Pro Preview: 37.7 (#33), GLM-4.5-Air: —

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#9), GLM-4.5-Air: 23.3 (#166)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
LMArena Hard Prompts14841379
ForecastBench5959.2
ARC-AGI-277.1%—
SimpleBench79.6%—
Kagi LLM Benchmark—43%
NYT Connections (extended)97.4%—
ARC-AGI-198%—
CritPt17.7%—
Chess Puzzles55%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
DTBench97.1%—
LMCA53.8%—
Epoch Capabilities Index154.92—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 61.8 (#28), GLM-4.5-Air: 33.8 (#166)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
LMArena Math14851396
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
OTIS Mock AIME 2024-202595.6%—
ProofBench26%—
Omni-MATH—39.1%
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), GLM-4.5-Air: 34.6 (#184)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
Humanity's Last Exam46.4%8.1%
Vectara Hallucination Rate10.4%9.3%
LMArena Expert14841370
GPQA Diamond94.4%—
SimpleQA Verified73.5%—
MMLU-Pro—76.2%
GPQA (HELM)—59.4%

Multimodal Not comparable

Gemini 3.1 Pro Preview: 38.1 (#60), GLM-4.5-Air: —

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.1 (#11), GLM-4.5-Air: 49.4 (#130)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
LMArena Non-English14751366
LMArena Chinese15281427
LMArena French14881399
LMArena German14911376
LMArena Japanese14941348
LMArena Korean14581306
LMArena Russian14961373
LMArena Spanish14801385

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.1 (#31), GLM-4.5-Air: 69.8 (#165)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
LMArena Instruction Following14651353
IFEval—81.2%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.3 (#17), GLM-4.5-Air: 41.6 (#130)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
LMArena Longer Query14821367
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.3 (#36), GLM-4.5-Air: 56.1 (#134)

BenchmarkGemini 3.1 Pro PreviewGLM-4.5-Air
LMArena Text14801384
LMArena Creative Writing14821343
LMArena Multi-Turn14861371
EQ-Bench Creative Writing1491—
WildBench—78.9%
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than GLM-4.5-Air?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 38.7 on the Noometry Index. GLM-4.5-Air costs 11× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview 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; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or GLM-4.5-Air better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3.1 Pro Preview and GLM-4.5-Air share?

21 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and GLM-4.5-Air has 27.

Related comparisons

Go deeper