Noometry

Model comparison

Deepseek Coder v2 vs GPT-5.2

GPT-5.2 is the stronger model overall, scoring 54.1 to 35.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.3

Rank #217 Confirmed

GPT-5.2 OpenAI

54.1

Rank #31 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GPT-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.2 leads 67.0 to 38.4.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2GPT-5.2
ProviderDeepSeekOpenAI
Noometry Index35.354.1
Released2024-06-172025-12-11
WeightsOpenProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$1.75
Output $ / M tokens—$14
Results tracked2467

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

Category by category

Coding GPT-5.2 leads

Deepseek Coder v2: 37.5 (#178), GPT-5.2: 52.2 (#32)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Coding12511447
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—72.8%
LMArena WebDev—1415
SWE-bench Multilingual—66.7%
GSO—27.4%
WeirdML—72.2%
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
ALE-Bench—1,294
AlgoTune—2.05
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, GPT-5.2: 40.0 (#24)

BenchmarkDeepseek Coder v2GPT-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 Coder v2: 22.6 (#175), GPT-5.2: 50.1 (#33)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Hard Prompts12071445
ARC-AGI-2—52.9%
SimpleBench—45.8%
Kagi LLM Benchmark—73.3%
NYT Connections (extended)—83.6%
ARC-AGI-1—86.2%
Chess Puzzles—49%
EnigmaEval—10.4%
EBR-Bench—23%
Mystery Game Puzzles—23%
DTBench—90.9%
LMCA—43.9%
Epoch Capabilities Index—153.45
ForecastBench—60.1
WinoGrande83.7%—

Math GPT-5.2 leads

Deepseek Coder v2: 32.3 (#188), GPT-5.2: 59.8 (#32)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Math12411439
FrontierMath (Tiers 1-3)—67.4%
FrontierMath Tier 4—31.7%
MathArena Final-Answer Competitions—72%
OTIS Mock AIME 2024-2025—96.1%
ProofBench—15%
FrontierMath (Feb 2025 set)—40.7%
FrontierMath Tier 4 (v1)—18.8%
GSM8K94.5%—

Knowledge GPT-5.2 leads

Deepseek Coder v2: 31.7 (#209), GPT-5.2: 59.2 (#29)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Expert11811445
GPQA Diamond—91.4%
Humanity's Last Exam—27.8%
SimpleQA Verified—37.1%
Vectara Hallucination Rate—8.4%
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, GPT-5.2: 50.9 (#7)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Vision—1268
VPCT—84%
Furniture Assembly—38.3%
LMArena Document—1405

Multilingual GPT-5.2 leads

Deepseek Coder v2: 36.4 (#235), GPT-5.2: 53.6 (#63)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Non-English11821425
LMArena Chinese12011460
LMArena French11841456
LMArena German11641448
LMArena Japanese11261421
LMArena Korean11041390
LMArena Russian11881440
LMArena Spanish11531433

Instruction Following GPT-5.2 leads

Deepseek Coder v2: 61.9 (#237), GPT-5.2: 74.9 (#83)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Instruction Following11801417

Long Context GPT-5.2 leads

Deepseek Coder v2: 37.0 (#219), GPT-5.2: 44.0 (#74)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Longer Query12191428
CL-bench—18.2%

Writing & Preference GPT-5.2 leads

Deepseek Coder v2: 38.4 (#249), GPT-5.2: 67.0 (#30)

BenchmarkDeepseek Coder v2GPT-5.2
LMArena Text11911439
LMArena Creative Writing11201402
LMArena Multi-Turn11761458
EQ-Bench Creative Writing—1703

Frequently asked questions

Is Deepseek Coder v2 better than GPT-5.2?

GPT-5.2 is the stronger model overall, scoring 54.1 to 35.3 on the Noometry Index.

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

GPT-5.2 scores higher on coding benchmarks: 52.2 versus 37.5 in the Noometry coding category.

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

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GPT-5.2 has 67.

Related comparisons

Go deeper