Noometry

Model comparison

DeepSeek LLM 67B vs GPT-5.2

GPT-5.2 is the stronger model overall, scoring 54.1 to 24.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GPT-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.2 leads 59.3 to 7.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 96.1% for GPT-5.2.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGPT-5.2
ProviderDeepSeekOpenAI
Noometry Index24.954.1
Released2023-11-292025-12-11
WeightsOpenProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$1.75
Output $ / M tokens—$14
Results tracked1567

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

Category by category

Coding GPT-5.2 leads

DeepSeek LLM 67B: 31.9 (#278), GPT-5.2: 51.6 (#37)

BenchmarkDeepSeek LLM 67BGPT-5.2
LMArena Coding10961447
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—72.8%
LMArena WebDev—1416
SWE-bench Multilingual—66.7%
GSO—27.4%
WeirdML—72.2%
ALE-Bench—1,294
AlgoTune—2.05

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, GPT-5.2: 40.2 (#24)

BenchmarkDeepSeek LLM 67BGPT-5.2
Terminal-Bench—64.9%
Berkeley Function Calling Leaderboard—55.9%
GDPval—49.7%
Remote Labor Index—2.5%
τ²-bench Airline—83%
τ²-bench Banking—32.2%
τ²-bench Retail—81.6%
τ²-bench Telecom—89.7%
DeepResearch Bench—41.1%
LMArena Search—1207
METR Time Horizons—75.3%
Vending-Bench 2—3,591

Reasoning GPT-5.2 leads

DeepSeek LLM 67B: 16.5 (#304), GPT-5.2: 50.2 (#35)

BenchmarkDeepSeek LLM 67BGPT-5.2
Chess Puzzles0%49%
LMArena Hard Prompts10701445
Epoch Capabilities Index110.5153.45
ARC-AGI-2—52.9%
SimpleBench—45.8%
Kagi LLM Benchmark—73.3%
NYT Connections (extended)—83.6%
ARC-AGI-1—86.2%
EnigmaEval—10.4%
EBR-Bench—23%
Mystery Game Puzzles—23%
DTBench—90.9%
LMCA—43.9%
ForecastBench—60.1

Math GPT-5.2 leads

DeepSeek LLM 67B: 8.7 (#324), GPT-5.2: 60.0 (#38)

BenchmarkDeepSeek LLM 67BGPT-5.2
OTIS Mock AIME 2024-20250.8%96.1%
LMArena Math11081440
FrontierMath (Tiers 1-3)—67.4%
FrontierMath Tier 4—31.7%
MathArena Final-Answer Competitions—72%
ProofBench—15%
MATH Level 56.4%—
FrontierMath (Feb 2025 set)—40.7%
FrontierMath Tier 4 (v1)—18.8%

Knowledge GPT-5.2 leads

DeepSeek LLM 67B: 7.0 (#313), GPT-5.2: 59.3 (#32)

BenchmarkDeepSeek LLM 67BGPT-5.2
GPQA Diamond24.6%91.4%
Humanity's Last Exam—27.8%
SimpleQA Verified—37.1%
Vectara Hallucination Rate—8.4%
LMArena Expert—1445

Multimodal Not comparable

DeepSeek LLM 67B: —, GPT-5.2: 51.3 (#7)

BenchmarkDeepSeek LLM 67BGPT-5.2
LMArena Vision—1268
VPCT—84%
Furniture Assembly—38.3%
LMArena Document—1405

Multilingual GPT-5.2 leads

DeepSeek LLM 67B: 29.4 (#267), GPT-5.2: 53.4 (#67)

BenchmarkDeepSeek LLM 67BGPT-5.2
LMArena Non-English10731425
LMArena Chinese11321460
LMArena French—1455
LMArena German—1448
LMArena Japanese—1420
LMArena Korean—1392
LMArena Russian—1440
LMArena Spanish—1433

Instruction Following GPT-5.2 leads

DeepSeek LLM 67B: 55.4 (#277), GPT-5.2: 74.7 (#89)

BenchmarkDeepSeek LLM 67BGPT-5.2
LMArena Instruction Following10791417

Long Context GPT-5.2 leads

DeepSeek LLM 67B: 33.1 (#265), GPT-5.2: 44.0 (#78)

BenchmarkDeepSeek LLM 67BGPT-5.2
LMArena Longer Query10921428
CL-bench—18.2%

Writing & Preference GPT-5.2 leads

DeepSeek LLM 67B: 31.6 (#282), GPT-5.2: 66.8 (#32)

BenchmarkDeepSeek LLM 67BGPT-5.2
LMArena Text11051439
LMArena Creative Writing10671401
LMArena Multi-Turn10821458
EQ-Bench Creative Writing—1703

Frequently asked questions

Is DeepSeek LLM 67B better than GPT-5.2?

GPT-5.2 is the stronger model overall, scoring 54.1 to 24.9 on the Noometry Index.

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

GPT-5.2 scores higher on coding benchmarks: 51.6 versus 31.9 in the Noometry coding category.

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

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

Related comparisons

Go deeper