Noometry

Model comparison

Deepseek Coder v2 vs GPT-5.4 mini

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GPT-5.4 mini in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.4 mini leads 64.0 to 38.2.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2GPT-5.4 mini
ProviderDeepSeekOpenAI
Noometry Index35.945.0
Released2024-06-172026-03-17
WeightsOpenProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$0.75
Output $ / M tokens—$4.50
Results tracked2446

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

Category by category

Coding GPT-5.4 mini leads

Deepseek Coder v2: 38.1 (#183), GPT-5.4 mini: 45.2 (#72)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Coding12511438
FrontierCode—27%
LMArena WebDev—1397
SciCode—49.9%
WeirdML—60.3%
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
ALE-Bench—1,189
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, GPT-5.4 mini: 29.9 (#81)

BenchmarkDeepseek Coder v2GPT-5.4 mini
DeepResearch Bench—36.3%

Reasoning GPT-5.4 mini leads

Deepseek Coder v2: 23.6 (#176), GPT-5.4 mini: 30.4 (#85)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Hard Prompts12071424
ARC-AGI-2—18.9%
Kagi LLM Benchmark—37.9%
NYT Connections (extended)—61.8%
ARC-AGI-1—63.7%
CritPt—10%
Chess Puzzles—24%
Thematic Generalization—61.7%
Mystery Game Puzzles—11%
DTBench—80%
LMCA—40.8%
Epoch Capabilities Index—148.84
ForecastBench—57
WinoGrande83.7%—

Math GPT-5.4 mini leads

Deepseek Coder v2: 34.9 (#190), GPT-5.4 mini: 45.5 (#75)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Math12411419
FrontierMath (Tiers 1-3)—51.2%
FrontierMath Tier 4—9.8%
OTIS Mock AIME 2024-2025—88.9%
ProofBench—21%
FrontierMath (Feb 2025 set)—28.3%
FrontierMath Tier 4 (v1)—2.1%
GSM8K94.5%—

Knowledge GPT-5.4 mini leads

Deepseek Coder v2: 32.3 (#212), GPT-5.4 mini: 51.5 (#67)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Expert11811435
GPQA Diamond—86.9%
SimpleQA Verified—29.4%
Vectara Hallucination Rate—5.5%
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, GPT-5.4 mini: 39.7 (#56)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Vision—1245

Multilingual GPT-5.4 mini leads

Deepseek Coder v2: 36.3 (#240), GPT-5.4 mini: 51.9 (#96)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Non-English11821405
LMArena Chinese12011446
LMArena French11851440
LMArena German11641409
LMArena Japanese11261374
LMArena Korean11041368
LMArena Russian11881417
LMArena Spanish11531405

Instruction Following GPT-5.4 mini leads

Deepseek Coder v2: 61.7 (#242), GPT-5.4 mini: 74.1 (#102)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Instruction Following11801405

Long Context GPT-5.4 mini leads

Deepseek Coder v2: 37.0 (#224), GPT-5.4 mini: 43.0 (#112)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Longer Query12191407

Writing & Preference GPT-5.4 mini leads

Deepseek Coder v2: 38.2 (#253), GPT-5.4 mini: 64.0 (#58)

BenchmarkDeepseek Coder v2GPT-5.4 mini
LMArena Text11911412
LMArena Creative Writing11201370
LMArena Multi-Turn11771429
EQ-Bench Creative Writing—1665

Frequently asked questions

Is Deepseek Coder v2 better than GPT-5.4 mini?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or GPT-5.4 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and GPT-5.4 mini share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GPT-5.4 mini has 46.

Related comparisons

Go deeper