Noometry

Model comparison

Deepseek Coder v2 vs GLM-5.2

GLM-5.2 is the stronger model overall, scoring 51.1 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

GLM-5.2 Z.ai (Zhipu)

51.1

Rank #44 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-5.2 leads 70.4 to 38.2.

Side by side

Deepseek Coder v2GLM-5.2
ProviderDeepSeekZ.ai (Zhipu)
Noometry Index35.951.1
Released2024-06-172026-06-13
WeightsOpenOpen
Context window—1M
Max output—131K
Input $ / M tokens—$1.40
Output $ / M tokens—$4.40
Results tracked2451

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

Category by category

Coding GLM-5.2 leads

Deepseek Coder v2: 38.1 (#183), GLM-5.2: 51.3 (#41)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Coding12511485
SWE-bench Verified—78.7%
DeepSWE—43.8%
FrontierCode—24.5%
LMArena WebDev—1603
SciCode—50.5%
WeirdML—70.1%
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
ALE-Bench—1,047
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, GLM-5.2: 32.4 (#63)

BenchmarkDeepseek Coder v2GLM-5.2
APEX-Agents—45.2%
τ²-bench Banking—37.1%
PostTrainBench—31.7%
GBAEval—0%
Vending-Bench 2—8,314

Reasoning GLM-5.2 leads

Deepseek Coder v2: 23.6 (#176), GLM-5.2: 42.3 (#52)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Hard Prompts12071480
ARC-AGI-2—22.8%
SimpleBench—58.8%
Kagi LLM Benchmark—62.6%
NYT Connections (extended)—74.3%
ARC-AGI-1—77%
CritPt—20.9%
Chess Puzzles—21%
EBR-Bench—9.5%
Mystery Game Puzzles—19%
DTBench—93.6%
LMCA—45.8%
Surface Evolver Bench—55.6%
Epoch Capabilities Index—151.78
WinoGrande83.7%—

Math GLM-5.2 leads

Deepseek Coder v2: 34.9 (#190), GLM-5.2: 55.7 (#43)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Math12411482
FrontierMath (Tiers 1-3)—59.2%
FrontierMath Tier 4—29.3%
MathArena Final-Answer Competitions—67.6%
OTIS Mock AIME 2024-2025—86.4%
ProofBench—35%
GSM8K94.5%—

Knowledge GLM-5.2 leads

Deepseek Coder v2: 32.3 (#212), GLM-5.2: 57.1 (#40)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Expert11811486
GPQA Diamond—91.9%
SimpleQA Verified—34.2%
ARC (AI2) Challenge64.3%—

Multilingual GLM-5.2 leads

Deepseek Coder v2: 36.3 (#240), GLM-5.2: 55.8 (#26)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Non-English11821459
LMArena Chinese12011519
LMArena French11851479
LMArena German11641468
LMArena Japanese11261451
LMArena Korean11041445
LMArena Russian11881466
LMArena Spanish11531477

Instruction Following GLM-5.2 leads

Deepseek Coder v2: 61.7 (#242), GLM-5.2: 76.9 (#34)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Instruction Following11801465

Long Context GLM-5.2 leads

Deepseek Coder v2: 37.0 (#224), GLM-5.2: 45.3 (#43)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Longer Query12191479

Writing & Preference GLM-5.2 leads

Deepseek Coder v2: 38.2 (#253), GLM-5.2: 70.4 (#21)

BenchmarkDeepseek Coder v2GLM-5.2
LMArena Text11911470
LMArena Creative Writing11201462
LMArena Multi-Turn11771469
EQ-Bench Creative Writing—1757
EQ-Bench 4—1222

Frequently asked questions

Is Deepseek Coder v2 better than GLM-5.2?

GLM-5.2 is the stronger model overall, scoring 51.1 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and GLM-5.2 share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GLM-5.2 has 51.

Related comparisons

Go deeper