Model comparison

DeepSeek-V3.1 vs GPT-4.1 mini

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 33.5 on the Noometry Index.

Last verified October 10, 2026. 24 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.2

Rank #106 Confirmed

GPT-4.1 mini OpenAI

33.5

Rank #232 Confirmed

Summary

They share 24 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and GPT-4.1 mini in 0 categories; 7 gaps are clear of the uncertainty.
The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.3 to 10.9.
The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 68.8% for GPT-4.1 mini.
DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
GPT-4.1 mini accepts more context: 1.05M tokens versus 164K.
DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1 and GPT-4.1 mini specifications
	DeepSeek-V3.1	GPT-4.1 mini
Provider	DeepSeek	OpenAI
Noometry Index	42.2	33.5
Released	2025-08-21	2025-04-14
Weights	Open	Proprietary
Context window	164K	1.05M
Max output	8K	33K
Input $ / M tokens	$0.25	$0.40
Output $ / M tokens	$0.95	$1.60
Results tracked	27	47

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 39.8 (#140), GPT-4.1 mini: 30.4 (#286)

Coding benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
WeirdML	38.4%	37.6%
LMArena Coding	1417	1367
SWE-bench Verified (bash only)	—	23.9%
Aider Polyglot	—	32.4%
SciCode	—	40.4%
BigCodeBench Instruct	—	48.9%
CadEval	—	16%

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, GPT-4.1 mini: 33.0 (#52)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
Berkeley Function Calling Leaderboard	—	50.5%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), GPT-4.1 mini: 10.9 (#335)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
Kagi LLM Benchmark	53.2%	48.6%
LMArena Hard Prompts	1417	1349
DTBench	82.7%	68.8%
LMCA	24.3%	21.1%
Epoch Capabilities Index	139.92	135.01
ARC-AGI-2	—	0%
SimpleBench	40%	—
ARC-AGI-1	—	3.5%
CritPt	—	0%
Chess Puzzles	—	7%
Mystery Game Puzzles	—	7%
ForecastBench	58	—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.1 (#125), GPT-4.1 mini: 23.1 (#264)

Math benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
LMArena Math	1420	1343
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%

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), GPT-4.1 mini: 34.7 (#183)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
LMArena Expert	1403	1338
GPQA Diamond	—	65.8%
SimpleQA Verified	—	12.7%
MMLU-Pro	—	78.3%
Vectara Hallucination Rate	5.5%	—
GPQA (HELM)	—	61.4%

Multimodal Not comparable

DeepSeek-V3.1: —, GPT-4.1 mini: 35.2 (#77)

Multimodal benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
LMArena Vision	—	1181

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.8 (#100), GPT-4.1 mini: 45.9 (#161)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
LMArena Non-English	1400	1318
LMArena Chinese	1470	1329
LMArena French	1447	1357
LMArena German	1412	1349
LMArena Japanese	1374	1291
LMArena Korean	1337	1298
LMArena Russian	1405	1324
LMArena Spanish	1429	1319

Instruction Following Too close to call

DeepSeek-V3.1: 74.1 (#105), GPT-4.1 mini: 73.9 (#113)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
LMArena Instruction Following	1400	1332
IFEval	—	90.4%

Long Context DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.3 (#227), GPT-4.1 mini: 31.8 (#270)

Long Context benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
Fiction.LiveBench	52.8%	44.4%
LMArena Longer Query	1422	1344

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.5 (#93), GPT-4.1 mini: 48.8 (#193)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 mini
LMArena Text	1420	1341
LMArena Creative Writing	1401	1300
EQ-Bench Creative Writing	1436	1147
LMArena Multi-Turn	1408	1354
WildBench	—	83.8%

Frequently asked questions

Is DeepSeek-V3.1 better than GPT-4.1 mini?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 33.5 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or GPT-4.1 mini?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

Is DeepSeek-V3.1 or GPT-4.1 mini better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 30.4 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and GPT-4.1 mini share?

24 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-4.1 mini has 47.