Noometry

Model comparison

DeepSeek LLM 67B vs GLM-5.2

GLM-5.2 is the stronger model overall, scoring 50.9 to 24.8 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.8

Rank #341 Confirmed

GLM-5.2 Z.ai (Zhipu)

50.9

Rank #38 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 7.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 86.4% for GLM-5.2.

Side by side

DeepSeek LLM 67BGLM-5.2
ProviderDeepSeekZ.ai (Zhipu)
Noometry Index24.850.9
Released2023-11-292026-06-13
WeightsOpenOpen
Context window—1M
Max output—131K
Input $ / M tokens—$1.40
Output $ / M tokens—$4.40
Results tracked1550

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

Category by category

Coding GLM-5.2 leads

DeepSeek LLM 67B: 31.3 (#273), GLM-5.2: 50.9 (#37)

BenchmarkDeepSeek LLM 67BGLM-5.2
LMArena Coding10961484
SWE-bench Verified—78.7%
DeepSWE—43.8%
FrontierCode—24.5%
LMArena WebDev—1604
SciCode—50.5%
WeirdML—70.1%
ALE-Bench—1,047

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, GLM-5.2: 31.6 (#63)

BenchmarkDeepSeek LLM 67BGLM-5.2
τ²-bench Banking—37.1%
PostTrainBench—31.7%
GBAEval—0%
Vending-Bench 2—8,314

Reasoning GLM-5.2 leads

DeepSeek LLM 67B: 15.9 (#300), GLM-5.2: 42.1 (#46)

BenchmarkDeepSeek LLM 67BGLM-5.2
Chess Puzzles0%21%
LMArena Hard Prompts10701480
Epoch Capabilities Index110.54151.76
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%
EBR-Bench—9.5%
Mystery Game Puzzles—19%
DTBench—93.6%
LMCA—45.8%
Surface Evolver Bench—55.6%

Math GLM-5.2 leads

DeepSeek LLM 67B: 8.1 (#318), GLM-5.2: 55.4 (#35)

BenchmarkDeepSeek LLM 67BGLM-5.2
OTIS Mock AIME 2024-20250.8%86.4%
LMArena Math11081482
FrontierMath (Tiers 1-3)—59.2%
FrontierMath Tier 4—29.3%
MathArena Final-Answer Competitions—67.6%
ProofBench—35%
MATH Level 56.4%—

Knowledge GLM-5.2 leads

DeepSeek LLM 67B: 7.1 (#308), GLM-5.2: 57.1 (#36)

BenchmarkDeepSeek LLM 67BGLM-5.2
GPQA Diamond24.6%91.9%
SimpleQA Verified—34.2%
LMArena Expert—1484

Multilingual GLM-5.2 leads

DeepSeek LLM 67B: 29.5 (#262), GLM-5.2: 56.0 (#25)

BenchmarkDeepSeek LLM 67BGLM-5.2
LMArena Non-English10731459
LMArena Chinese11321518
LMArena French—1476
LMArena German—1470
LMArena Japanese—1451
LMArena Korean—1445
LMArena Russian—1467
LMArena Spanish—1477

Instruction Following GLM-5.2 leads

DeepSeek LLM 67B: 55.7 (#272), GLM-5.2: 77.1 (#32)

BenchmarkDeepSeek LLM 67BGLM-5.2
LMArena Instruction Following10791465

Long Context GLM-5.2 leads

DeepSeek LLM 67B: 33.1 (#260), GLM-5.2: 45.3 (#43)

BenchmarkDeepSeek LLM 67BGLM-5.2
LMArena Longer Query10921479

Writing & Preference GLM-5.2 leads

DeepSeek LLM 67B: 31.8 (#277), GLM-5.2: 70.7 (#20)

BenchmarkDeepSeek LLM 67BGLM-5.2
LMArena Text11051470
LMArena Creative Writing10671465
LMArena Multi-Turn10821468
EQ-Bench Creative Writing—1757
EQ-Bench 4—1222

Frequently asked questions

Is DeepSeek LLM 67B better than GLM-5.2?

GLM-5.2 is the stronger model overall, scoring 50.9 to 24.8 on the Noometry Index.

Is DeepSeek LLM 67B or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 31.3 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and GLM-5.2 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-5.2 has 50.

Related comparisons

Go deeper