Noometry

Model comparison

Gemini 3.1 Pro Preview vs GLM-5

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.9 on the Noometry Index. GLM-5 costs 2.9× 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 . 39 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #20 Confirmed

GLM-5 Z.ai (Zhipu)

45.9

Rank #59 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and GLM-5 in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 27.6.
  • The biggest single-benchmark swing is ARC-AGI-2: 77.1% for Gemini 3.1 Pro Preview and 4.9% for GLM-5.
  • GLM-5 is cheaper at $1 / $3.20 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 205K.
  • GLM-5 has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewGLM-5
ProviderGoogleZ.ai (Zhipu)
Noometry Index56.745.9
Released2026-02-192026-02-11
WeightsProprietaryOpen
Context window1.05M205K
Max output66K131K
Input $ / M tokens$2$1
Output $ / M tokens$12$3.20
Results tracked7145

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

Category by category

Coding GLM-5 leads

Gemini 3.1 Pro Preview: 42.7 (#88), GLM-5: 49.0 (#47)

BenchmarkGemini 3.1 Pro PreviewGLM-5
SWE-bench Verified75.6%72.1%
LMArena WebDev14461434
WeirdML72.1%48.2%
LMArena Coding14831461
ALE-Bench1,161765.62
DeepSWE11.7%—
SWE-bench Verified (bash only)—72.8%
SWE-bench Multilingual—69.7%
SciCode58.9%—
GSO22.6%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#33), GLM-5: 30.9 (#65)

BenchmarkGemini 3.1 Pro PreviewGLM-5
Terminal-Bench80.2%52.4%
τ²-bench Banking26%9.8%
Vending-Bench 23,7744,432
APEX-Agents35.3%—
τ²-bench Airline—82.5%
τ²-bench Retail—73.7%
τ²-bench Telecom—86.8%
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#9), GLM-5: 27.6 (#100)

BenchmarkGemini 3.1 Pro PreviewGLM-5
ARC-AGI-277.1%4.9%
SimpleBench79.6%53.2%
NYT Connections (extended)97.4%74.8%
ARC-AGI-198%44.7%
Chess Puzzles55%10%
LMArena Hard Prompts14841451
Epoch Capabilities Index154.92145.84
ForecastBench5961
Kagi LLM Benchmark—75%
CritPt17.7%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
DTBench97.1%—
LMCA53.8%—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 61.8 (#28), GLM-5: 44.8 (#66)

BenchmarkGemini 3.1 Pro PreviewGLM-5
MathArena Final-Answer Competitions86.5%65.7%
OTIS Mock AIME 2024-202595.6%80%
LMArena Math14851440
FrontierMath (Feb 2025 set)36.9%16.4%
FrontierMath Tier 4 (v1)16.7%2.1%
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
ProofBench26%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), GLM-5: 52.2 (#59)

BenchmarkGemini 3.1 Pro PreviewGLM-5
GPQA Diamond94.4%87.8%
Vectara Hallucination Rate10.4%10.1%
LMArena Expert14841454
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—

Multimodal Not comparable

Gemini 3.1 Pro Preview: 38.1 (#60), GLM-5: —

BenchmarkGemini 3.1 Pro PreviewGLM-5
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-5: 53.9 (#57)

BenchmarkGemini 3.1 Pro PreviewGLM-5
LMArena Non-English14751430
LMArena Chinese15281511
LMArena French14881455
LMArena German14911445
LMArena Japanese14941416
LMArena Korean14581421
LMArena Russian14961436
LMArena Spanish14801452

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.1 (#31), GLM-5: 75.4 (#64)

BenchmarkGemini 3.1 Pro PreviewGLM-5
LMArena Instruction Following14651427

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.3 (#17), GLM-5: 44.6 (#58)

BenchmarkGemini 3.1 Pro PreviewGLM-5
CL-bench20.8%18.7%
LMArena Longer Query14821446
CL-bench Life16.9%—

Writing & Preference Too close to call

Gemini 3.1 Pro Preview: 66.3 (#36), GLM-5: 66.2 (#38)

BenchmarkGemini 3.1 Pro PreviewGLM-5
LMArena Text14801446
LMArena Creative Writing14821438
EQ-Bench Creative Writing14911601
LMArena Multi-Turn14861456
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than GLM-5?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.9 on the Noometry Index. GLM-5 costs 2.9× 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-5?

GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or GLM-5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 42.7 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 205K.

How many benchmarks do Gemini 3.1 Pro Preview and GLM-5 share?

39 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and GLM-5 has 45.

Related comparisons

Go deeper