Noometry

Model comparison

Gemini 3.8 Flash vs GLM-5.3

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.8 on the Noometry Index.

Last verified . 41 shared benchmarks.

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

GLM-5.3 Z.ai (Zhipu)

54.8

Rank #26 Confirmed

Summary

  • They share 41 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 7 categories and GLM-5.3 in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 46.1.
  • The biggest single-benchmark swing is Chess Puzzles: 61% for Gemini 3.8 Flash and 21% for GLM-5.3.
  • Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.40 / $4.40 for GLM-5.3.
  • Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.
  • GLM-5.3 has downloadable open weights; the other is API-only.

Side by side

Gemini 3.8 FlashGLM-5.3
ProviderGoogleZ.ai (Zhipu)
Noometry Index61.854.8
Released2026-09-022026-08-14
WeightsProprietaryOpen
Context window1.05M1M
Max output66K131K
Input $ / M tokens$0.75$1.40
Output $ / M tokens$3.75$4.40
Results tracked5042

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

Category by category

Coding Too close to call

Gemini 3.8 Flash: 59.2 (#15), GLM-5.3: 59.5 (#14)

BenchmarkGemini 3.8 FlashGLM-5.3
DeepSWE73.8%69%
FrontierCode41.2%40.1%
CursorBench39.6%42.6%
LMArena WebDev15841622
FrontierSWE19.6%30.2%
SciCode56.6%59%
WeirdML84.8%75.4%
LMArena Coding15101496
ALE-Bench1,2701,317

Agentic & Tool Use Gemini 3.8 Flash leads

Gemini 3.8 Flash: 41.8 (#21), GLM-5.3: 36.4 (#38)

BenchmarkGemini 3.8 FlashGLM-5.3
APEX-Agents64.3%56.6%
Vending-Bench 25,0948,164
Remote Labor Index5.8%—
GDP.pdf23.4%—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 76.9 (#5), GLM-5.3: 46.1 (#46)

BenchmarkGemini 3.8 FlashGLM-5.3
NYT Connections (extended)97.4%74.2%
CritPt18.3%19.1%
Chess Puzzles61%21%
LMArena Hard Prompts15081489
Mystery Game Puzzles47%33%
DTBench95.7%87.7%
LMCA52.9%55.5%
Epoch Capabilities Index156.71155.61
ARC-AGI-289.2%—
ARC-AGI-198.5%—
Surface Evolver Bench76.9%—
Bench to the Future 3—0.15

Math Gemini 3.8 Flash leads

Gemini 3.8 Flash: 65.3 (#28), GLM-5.3: 62.3 (#33)

BenchmarkGemini 3.8 FlashGLM-5.3
FrontierMath (Tiers 1-3)68.4%68.8%
FrontierMath Tier 422%29.3%
OTIS Mock AIME 2024-202598.9%91.1%
ProofBench48%49%
LMArena Math15281489

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.8 (#2), GLM-5.3: 58.3 (#37)

BenchmarkGemini 3.8 FlashGLM-5.3
GPQA Diamond95.4%90.9%
SimpleQA Verified69.7%41%
LMArena Expert15241516
Humanity's Last Exam44.5%—

Multimodal Not comparable

Gemini 3.8 Flash: 40.7 (#45), GLM-5.3: —

BenchmarkGemini 3.8 FlashGLM-5.3
LMArena Vision1314—
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—

Multilingual Gemini 3.8 Flash leads

Gemini 3.8 Flash: 58.0 (#5), GLM-5.3: 55.7 (#28)

BenchmarkGemini 3.8 FlashGLM-5.3
LMArena Non-English14911457
LMArena Chinese15541528
LMArena French14981499
LMArena German14931499
LMArena Japanese15021453
LMArena Korean14591472
LMArena Russian15151463
LMArena Spanish14851460

Instruction Following Too close to call

Gemini 3.8 Flash: 78.0 (#13), GLM-5.3: 77.5 (#23)

BenchmarkGemini 3.8 FlashGLM-5.3
LMArena Instruction Following14901477

Long Context Too close to call

Gemini 3.8 Flash: 46.3 (#24), GLM-5.3: 45.4 (#41)

BenchmarkGemini 3.8 FlashGLM-5.3
LMArena Longer Query15081482

Writing & Preference GLM-5.3 leads

Gemini 3.8 Flash: 72.2 (#15), GLM-5.3: 75.7 (#6)

BenchmarkGemini 3.8 FlashGLM-5.3
LMArena Text14991471
LMArena Creative Writing14921457
EQ-Bench Creative Writing17482075
LMArena Multi-Turn15011472

Frequently asked questions

Is Gemini 3.8 Flash better than GLM-5.3?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.8 on the Noometry Index.

Which is cheaper, Gemini 3.8 Flash or GLM-5.3?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GLM-5.3 lists at $1.40 and $4.40.

Is Gemini 3.8 Flash or GLM-5.3 better for coding?

They score almost the same on coding (59.2 vs 59.5); test both on your own repository before choosing.

Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 1M.

How many benchmarks do Gemini 3.8 Flash and GLM-5.3 share?

41 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GLM-5.3 has 42.

Related comparisons

Go deeper