Noometry

Model comparison

Deepseek Coder v2 vs GPT-4.1 mini

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 33.6 on the Noometry Index.

Last verified . 18 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Deepseek Coder v2 scores higher in 4 categories and GPT-4.1 mini in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Deepseek Coder v2 leads 23.6 to 10.8.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2GPT-4.1 mini
ProviderDeepSeekOpenAI
Noometry Index35.933.6
Released2024-06-172025-04-14
WeightsOpenProprietary
Context window—1.05M
Max output—33K
Input $ / M tokens—$0.40
Output $ / M tokens—$1.60
Results tracked2447

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

Category by category

Coding Deepseek Coder v2 leads

Deepseek Coder v2: 38.1 (#183), GPT-4.1 mini: 30.6 (#293)

BenchmarkDeepseek Coder v2GPT-4.1 mini
BigCodeBench Instruct48.2%48.9%
LMArena Coding12511367
SWE-bench Verified (bash only)—23.9%
Aider Polyglot—32.4%
SciCode—40.4%
WeirdML—37.6%
BigCodeBench Complete59.7%—
CadEval—16%
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, GPT-4.1 mini: 33.3 (#55)

BenchmarkDeepseek Coder v2GPT-4.1 mini
Berkeley Function Calling Leaderboard—50.5%

Reasoning Deepseek Coder v2 leads

Deepseek Coder v2: 23.6 (#176), GPT-4.1 mini: 10.8 (#340)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Hard Prompts12071349
ARC-AGI-2—0%
Kagi LLM Benchmark—48.6%
ARC-AGI-1—3.5%
CritPt—0%
Chess Puzzles—7%
Mystery Game Puzzles—7%
DTBench—68.8%
LMCA—21.1%
Epoch Capabilities Index—135.01
WinoGrande83.7%—

Math Deepseek Coder v2 leads

Deepseek Coder v2: 34.9 (#190), GPT-4.1 mini: 24.1 (#270)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Math12411343
FrontierMath (Tiers 1-3)—6.7%
OTIS Mock AIME 2024-2025—44.7%
Omni-MATH—49.1%
MATH Level 5—87.3%
FrontierMath (Feb 2025 set)—4.5%
GSM8K94.5%—

Knowledge GPT-4.1 mini leads

Deepseek Coder v2: 32.3 (#212), GPT-4.1 mini: 34.7 (#194)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Expert11811338
GPQA Diamond—65.8%
SimpleQA Verified—12.7%
MMLU-Pro—78.3%
GPQA (HELM)—61.4%
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, GPT-4.1 mini: 35.8 (#82)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Vision—1181

Multilingual GPT-4.1 mini leads

Deepseek Coder v2: 36.3 (#240), GPT-4.1 mini: 45.7 (#166)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Non-English11821318
LMArena Chinese12011329
LMArena French11851358
LMArena German11641351
LMArena Japanese11261290
LMArena Korean11041298
LMArena Russian11881324
LMArena Spanish11531319

Instruction Following GPT-4.1 mini leads

Deepseek Coder v2: 61.7 (#242), GPT-4.1 mini: 73.7 (#118)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Instruction Following11801333
IFEval—90.4%

Long Context Deepseek Coder v2 leads

Deepseek Coder v2: 37.0 (#224), GPT-4.1 mini: 31.8 (#275)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Longer Query12191344
Fiction.LiveBench—44.4%

Writing & Preference GPT-4.1 mini leads

Deepseek Coder v2: 38.2 (#253), GPT-4.1 mini: 48.6 (#199)

BenchmarkDeepseek Coder v2GPT-4.1 mini
LMArena Text11911340
LMArena Creative Writing11201300
LMArena Multi-Turn11771354
EQ-Bench Creative Writing—1147
WildBench—83.8%

Frequently asked questions

Is Deepseek Coder v2 better than GPT-4.1 mini?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 33.6 on the Noometry Index.

Is Deepseek Coder v2 or GPT-4.1 mini better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 30.6 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and GPT-4.1 mini share?

18 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GPT-4.1 mini has 47.

Related comparisons

Go deeper