Noometry

Model comparison

DeepSeek Coder 6.7B vs GLM-5.2

GLM-5.2 has enough public results to be ranked (#38); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

DeepSeek Coder 6.7B DeepSeek

37.1

Unranked Sparse

GLM-5.2 Z.ai (Zhipu)

50.9

Rank #38 Confirmed

Summary

  • They share 1 benchmark with published results for both. DeepSeek Coder 6.7B scores higher in 0 categories and GLM-5.2 in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where GLM-5.2 leads 50.9 to 35.2.

Side by side

DeepSeek Coder 6.7BGLM-5.2
ProviderDeepSeekZ.ai (Zhipu)
Noometry Index37.150.9
Released2023-11-022026-06-13
WeightsOpenOpen
Context window—1M
Max output—131K
Input $ / M tokens—$1.40
Output $ / M tokens—$4.40
Results tracked950

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

Category by category

Coding GLM-5.2 leads

DeepSeek Coder 6.7B: 35.2 (#216), GLM-5.2: 50.9 (#37)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
SWE-bench Verified—78.7%
DeepSWE—43.8%
FrontierCode—24.5%
LMArena WebDev—1604
SciCode—50.5%
WeirdML—70.1%
BigCodeBench Instruct35.5%—
LMArena Coding—1484
BigCodeBench Complete43.8%—
ALE-Bench—1,047
HumanEval+71.3%—
MBPP+65.6%—

Agentic & Tool Use Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 31.6 (#63)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
τ²-bench Banking—37.1%
PostTrainBench—31.7%
GBAEval—0%
Vending-Bench 2—8,314

Reasoning Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 42.1 (#46)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
Epoch Capabilities Index88.88151.76
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%
LMArena Hard Prompts—1480
Mystery Game Puzzles—19%
DTBench—93.6%
LMCA—45.8%
Surface Evolver Bench—55.6%
WinoGrande57.6%—

Math Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 55.4 (#35)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
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%
LMArena Math—1482
GSM8K21.3%—

Knowledge Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 57.1 (#36)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
GPQA Diamond—91.9%
SimpleQA Verified—34.2%
LMArena Expert—1484
ARC (AI2) Challenge36.4%—
MMLU36.4%—

Multilingual Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 56.0 (#25)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
LMArena Non-English—1459
LMArena Chinese—1518
LMArena French—1476
LMArena German—1470
LMArena Japanese—1451
LMArena Korean—1445
LMArena Russian—1467
LMArena Spanish—1477

Instruction Following Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 77.1 (#32)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
LMArena Instruction Following—1465

Long Context Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 45.3 (#43)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
LMArena Longer Query—1479

Writing & Preference Not comparable

DeepSeek Coder 6.7B: —, GLM-5.2: 70.7 (#20)

BenchmarkDeepSeek Coder 6.7BGLM-5.2
LMArena Text—1470
LMArena Creative Writing—1465
EQ-Bench Creative Writing—1757
EQ-Bench 4—1222
LMArena Multi-Turn—1468

Frequently asked questions

Is DeepSeek Coder 6.7B better than GLM-5.2?

GLM-5.2 has enough public results to be ranked (#38); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 6.7B or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 35.2 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 6.7B and GLM-5.2 share?

1 benchmark has published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and GLM-5.2 has 50.

Related comparisons

Go deeper