Noometry

Model comparison

Deepseek Coder v2 vs GPT-5.5

GPT-5.5 is the stronger model overall, scoring 63.4 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

GPT-5.5 OpenAI

63.4

Rank #9 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GPT-5.5 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.5 leads 72.8 to 23.6.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2GPT-5.5
ProviderDeepSeekOpenAI
Noometry Index35.963.4
Released2024-06-172026-04-23
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$5
Output $ / M tokens—$30
Results tracked2471

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

Category by category

Coding GPT-5.5 leads

Deepseek Coder v2: 38.1 (#183), GPT-5.5: 58.2 (#17)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Coding12511494
SWE-bench Verified—80.6%
DeepSWE—67%
FrontierCode—43%
LMArena WebDev—1513
SciCode—56.1%
GSO—40.2%
WeirdML—84.9%
BigCodeBench Instruct48.2%—
MirrorCode—10%
BigCodeBench Complete59.7%—
ALE-Bench—1,943
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, GPT-5.5: 50.7 (#6)

BenchmarkDeepseek Coder v2GPT-5.5
Terminal-Bench—84.7%
APEX-Agents—55.1%
OSWorld 2.0—13%
Remote Labor Index—6.3%
τ²-bench Banking—44.6%
DeepResearch Bench—54%
PostTrainBench—27.2%
ExploitBench—47.4%
GBAEval—53.2%
GDP.pdf—26%
LMArena Search—1242
Vending-Bench 2—7,524

Reasoning GPT-5.5 leads

Deepseek Coder v2: 23.6 (#176), GPT-5.5: 72.8 (#11)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Hard Prompts12071489
ARC-AGI-2—85%
SimpleBench—69%
Kagi LLM Benchmark—88.8%
NYT Connections (extended)—96.2%
ARC-AGI-1—95%
CritPt—27.1%
Chess Puzzles—54%
EBR-Bench—34.3%
Mystery Game Puzzles—56%
DTBench—96%
LMCA—54.3%
Surface Evolver Bench—88.1%
Bench to the Future 3—0.14
Epoch Capabilities Index—159.1
ForecastBench—60.6
WinoGrande83.7%—

Math GPT-5.5 leads

Deepseek Coder v2: 34.9 (#190), GPT-5.5: 81.7 (#11)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Math12411486
FrontierMath (Tiers 1-3)—85.3%
FrontierMath Tier 4—72.5%
MathArena Final-Answer Competitions—94.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—50%
FrontierMath (Feb 2025 set)—51.7%
FrontierMath Erdős—0%
FrontierMath Tier 4 (v1)—35.4%
GSM8K94.5%—

Knowledge GPT-5.5 leads

Deepseek Coder v2: 32.3 (#212), GPT-5.5: 64.4 (#17)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Expert11811508
GPQA Diamond—94%
SimpleQA Verified—63%
Vectara Hallucination Rate—9.3%
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, GPT-5.5: 46.9 (#12)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Vision—1297
Blueprint-Bench 2—36.2%
Furniture Assembly—44.2%
LMArena Document—1486

Multilingual GPT-5.5 leads

Deepseek Coder v2: 36.3 (#240), GPT-5.5: 56.4 (#20)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Non-English11821467
LMArena Chinese12011533
LMArena French11851486
LMArena German11641480
LMArena Japanese11261498
LMArena Korean11041460
LMArena Russian11881473
LMArena Spanish11531468

Instruction Following GPT-5.5 leads

Deepseek Coder v2: 61.7 (#242), GPT-5.5: 77.5 (#18)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Instruction Following11801479

Long Context GPT-5.5 leads

Deepseek Coder v2: 37.0 (#224), GPT-5.5: 48.3 (#12)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Longer Query12191484
CL-bench Life—22.2%

Writing & Preference GPT-5.5 leads

Deepseek Coder v2: 38.2 (#253), GPT-5.5: 72.7 (#13)

BenchmarkDeepseek Coder v2GPT-5.5
LMArena Text11911472
LMArena Creative Writing11201455
LMArena Multi-Turn11771476
EQ-Bench Creative Writing—1844
EQ-Bench 4—1315

Frequently asked questions

Is Deepseek Coder v2 better than GPT-5.5?

GPT-5.5 is the stronger model overall, scoring 63.4 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or GPT-5.5 better for coding?

GPT-5.5 scores higher on coding benchmarks: 58.2 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and GPT-5.5 share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GPT-5.5 has 71.

Related comparisons

Go deeper