Noometry

Model comparison

Gemini 2.5 Pro vs GLM-5.3-Flash

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 45.0 on the Noometry Index.

Last verified . 30 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

GLM-5.3-Flash Z.ai (Zhipu)

51.8

Rank #41 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 2 categories and GLM-5.3-Flash in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.3-Flash leads 53.3 to 32.5.
  • The biggest single-benchmark swing is ARC-AGI-2: 4.9% for Gemini 2.5 Pro and 65.8% for GLM-5.3-Flash.
  • GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.
  • GLM-5.3-Flash has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProGLM-5.3-Flash
ProviderGoogleZ.ai (Zhipu)
Noometry Index45.051.8
Released2025-03-252026-08-20
WeightsProprietaryOpen
Context window1.05M1M
Max output66K131K
Input $ / M tokens$1.25$0.15
Output $ / M tokens$10$0.50
Results tracked7840

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

Category by category

Coding GLM-5.3-Flash leads

Gemini 2.5 Pro: 42.4 (#101), GLM-5.3-Flash: 53.1 (#31)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
LMArena WebDev12271609
SciCode42.8%51.6%
LMArena Coding14521508
ALE-Bench785.52303.55
SWE-bench Verified57.6%—
DeepSWE—63.4%
FrontierCode—31.8%
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
CursorBench—36.8%
FrontierSWE—18.1%
GSO3.9%—
WeirdML54%—
LiveBench Coding85.9%—
CadEval64%—
AlgoTune1.51—

Agentic & Tool Use GLM-5.3-Flash leads

Gemini 2.5 Pro: 29.2 (#88), GLM-5.3-Flash: 34.2 (#47)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
Terminal-Bench32.6%—
APEX-Agents—52.8%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
GDP.pdf—14%
LMArena Search1142—
METR Time Horizons55.4%—
Vending-Bench 2573.64—

Reasoning GLM-5.3-Flash leads

Gemini 2.5 Pro: 28.8 (#99), GLM-5.3-Flash: 48.0 (#42)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
ARC-AGI-24.9%65.8%
ARC-AGI-141%91%
CritPt2%15.4%
Chess Puzzles20%14%
LMArena Hard Prompts14551491
Epoch Capabilities Index145.32151.88
SimpleBench62.4%—
Kagi LLM Benchmark70.3%—
EnigmaEval5.6%—
LiveBench Reasoning89.8%—
Mystery Game Puzzles—8%
DTBench82.4%—
LiveBench Data Analysis79.9%—
LMCA34.8%—
Surface Evolver Bench—52.5%
Bench to the Future 3—0.15
ForecastBench61.3—
LiveBench82.3%—

Math GLM-5.3-Flash leads

Gemini 2.5 Pro: 32.5 (#213), GLM-5.3-Flash: 53.3 (#47)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
FrontierMath (Tiers 1-3)24.6%55.8%
FrontierMath Tier 40%17.1%
OTIS Mock AIME 2024-202584.7%93.9%
LMArena Math14501500
ProofBench—21%
Omni-MATH41.6%—
LiveBench Math90.2%—
MATH Level 595.9%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge GLM-5.3-Flash leads

Gemini 2.5 Pro: 56.0 (#46), GLM-5.3-Flash: 58.4 (#36)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
GPQA Diamond85.3%90.2%
LMArena Expert14521513
Humanity's Last Exam21.6%—
MMLU-Pro86.3%—
Confabulations10.6%—
Vectara Hallucination Rate7%—
GPQA (HELM)74.9%—

Multimodal Gemini 2.5 Pro leads

Gemini 2.5 Pro: 45.2 (#18), GLM-5.3-Flash: 42.8 (#27)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
LMArena Vision12631296
GeoBench86%—
VPCT48%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Too close to call

Gemini 2.5 Pro: 55.3 (#31), GLM-5.3-Flash: 56.0 (#25)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
LMArena Non-English14511462
LMArena Chinese15071527
LMArena French14721496
LMArena German14871470
LMArena Japanese14611429
LMArena Korean14341446
LMArena Russian14611469
LMArena Spanish14731471

Instruction Following GLM-5.3-Flash leads

Gemini 2.5 Pro: 75.0 (#75), GLM-5.3-Flash: 77.5 (#20)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
LMArena Instruction Following14371478
LiveBench Instruction Following80.6%—
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), GLM-5.3-Flash: 45.4 (#39)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
LMArena Longer Query14491482
Fiction.LiveBench91.7%—

Writing & Preference GLM-5.3-Flash leads

Gemini 2.5 Pro: 63.7 (#62), GLM-5.3-Flash: 65.3 (#50)

BenchmarkGemini 2.5 ProGLM-5.3-Flash
LMArena Text14581471
LMArena Creative Writing14541442
LMArena Multi-Turn14531467
Short-Story Creative Writing83.8%—
EQ-Bench Creative Writing1421—
WildBench85.7%—
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than GLM-5.3-Flash?

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 45.0 on the Noometry Index.

Which is cheaper, Gemini 2.5 Pro or GLM-5.3-Flash?

GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or GLM-5.3-Flash better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 1M.

How many benchmarks do Gemini 2.5 Pro and GLM-5.3-Flash share?

30 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GLM-5.3-Flash has 40.

Related comparisons

Go deeper