Noometry

Model comparison

DeepSeek LLM 67B vs GLM-5.1

GLM-5.1 is the stronger model overall, scoring 47.8 to 24.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

GLM-5.1 Z.ai (Zhipu)

47.8

Rank #59 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GLM-5.1 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-5.1 leads 54.9 to 7.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 93.3% for GLM-5.1.

Side by side

DeepSeek LLM 67BGLM-5.1
ProviderDeepSeekZ.ai (Zhipu)
Noometry Index24.947.8
Released2023-11-292026-04-07
WeightsOpenOpen
Context window—200K
Max output—131K
Input $ / M tokens—$1.40
Output $ / M tokens—$4.40
Results tracked1541

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

Category by category

Coding GLM-5.1 leads

DeepSeek LLM 67B: 31.9 (#278), GLM-5.1: 48.7 (#55)

BenchmarkDeepSeek LLM 67BGLM-5.1
LMArena Coding10961485
SWE-bench Verified—74.2%
LMArena WebDev—1508
SciCode—43.8%
WeirdML—57.1%
ALE-Bench—887.1

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, GLM-5.1: 24.9 (#113)

BenchmarkDeepSeek LLM 67BGLM-5.1
APEX-Agents—40.9%
ExploitBench—18.1%
GBAEval—0%
Vending-Bench 2—5,634

Reasoning GLM-5.1 leads

DeepSeek LLM 67B: 16.5 (#304), GLM-5.1: 39.1 (#60)

BenchmarkDeepSeek LLM 67BGLM-5.1
Chess Puzzles0%19%
LMArena Hard Prompts10701472
Epoch Capabilities Index110.5149.84
SimpleBench—55.1%
NYT Connections (extended)—77.7%
CritPt—4.6%
Thematic Generalization—69.8%

Math GLM-5.1 leads

DeepSeek LLM 67B: 8.7 (#324), GLM-5.1: 49.7 (#60)

BenchmarkDeepSeek LLM 67BGLM-5.1
OTIS Mock AIME 2024-20250.8%93.3%
LMArena Math11081473
FrontierMath (Tiers 1-3)—36.8%
MathArena Final-Answer Competitions—67.1%
ProofBench—22.2%
MATH Level 56.4%—
FrontierMath (Feb 2025 set)—33.4%
FrontierMath Tier 4 (v1)—12.5%

Knowledge GLM-5.1 leads

DeepSeek LLM 67B: 7.0 (#313), GLM-5.1: 54.9 (#50)

BenchmarkDeepSeek LLM 67BGLM-5.1
GPQA Diamond24.6%89.9%
SimpleQA Verified—34%
LMArena Expert—1476

Multilingual GLM-5.1 leads

DeepSeek LLM 67B: 29.4 (#267), GLM-5.1: 55.0 (#36)

BenchmarkDeepSeek LLM 67BGLM-5.1
LMArena Non-English10731447
LMArena Chinese11321515
LMArena French—1474
LMArena German—1465
LMArena Japanese—1434
LMArena Korean—1418
LMArena Russian—1454
LMArena Spanish—1469

Instruction Following GLM-5.1 leads

DeepSeek LLM 67B: 55.4 (#277), GLM-5.1: 76.3 (#42)

BenchmarkDeepSeek LLM 67BGLM-5.1
LMArena Instruction Following10791451

Long Context GLM-5.1 leads

DeepSeek LLM 67B: 33.1 (#265), GLM-5.1: 44.9 (#53)

BenchmarkDeepSeek LLM 67BGLM-5.1
LMArena Longer Query10921466

Writing & Preference GLM-5.1 leads

DeepSeek LLM 67B: 31.6 (#282), GLM-5.1: 66.9 (#31)

BenchmarkDeepSeek LLM 67BGLM-5.1
LMArena Text11051461
LMArena Creative Writing10671453
LMArena Multi-Turn10821472
EQ-Bench Creative Writing—1592

Frequently asked questions

Is DeepSeek LLM 67B better than GLM-5.1?

GLM-5.1 is the stronger model overall, scoring 47.8 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or GLM-5.1 better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and GLM-5.1 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-5.1 has 41.

Related comparisons

Go deeper