Model comparison

DeepSeek-V3.1 vs GPT-4.1 nano

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 27.9 on the Noometry Index. GPT-4.1 nano costs 2.4× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

Last verified October 12, 2026. 21 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.8

Rank #108 Confirmed

GPT-4.1 nano OpenAI

27.9

Rank #327 Confirmed

Summary

They share 21 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and GPT-4.1 nano in 0 categories; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.7 to 21.8.
The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 52.5% for GPT-4.1 nano.
GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
GPT-4.1 nano 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 nano specifications
	DeepSeek-V3.1	GPT-4.1 nano
Provider	DeepSeek	OpenAI
Noometry Index	42.8	27.9
Released	2025-08-21	2025-04-14
Weights	Open	Proprietary
Context window	164K	1.05M
Max output	8K	33K
Input $ / M tokens	$0.25	$0.10
Output $ / M tokens	$0.95	$0.40
Results tracked	27	38

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 40.3 (#144), GPT-4.1 nano: 24.1 (#330)

Coding benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
WeirdML	38.4%	19%
LMArena Coding	1417	1306
Aider Polyglot	—	8.9%
SciCode	—	25.9%

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, GPT-4.1 nano: 26.5 (#104)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
Berkeley Function Calling Leaderboard	—	33%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.9 (#110), GPT-4.1 nano: 8.5 (#349)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
Kagi LLM Benchmark	53.2%	33.3%
LMArena Hard Prompts	1417	1286
DTBench	82.7%	52.5%
LMCA	24.3%	5.5%
Epoch Capabilities Index	139.92	129.62
ARC-AGI-2	—	0%
SimpleBench	40%	—
ARC-AGI-1	—	0%
CritPt	—	0%
ForecastBench	58	—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 38.9 (#122), GPT-4.1 nano: 26.9 (#252)

Math benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
LMArena Math	1420	1274
OTIS Mock AIME 2024-2025	—	28.9%
Omni-MATH	—	36.7%
MATH Level 5	—	70%
FrontierMath (Feb 2025 set)	—	1%

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.7 (#90), GPT-4.1 nano: 21.8 (#273)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
LMArena Expert	1405	1272
GPQA Diamond	—	48.9%
SimpleQA Verified	—	6%
MMLU-Pro	—	55%
Vectara Hallucination Rate	5.5%	—
GPQA (HELM)	—	50.7%

Multimodal Not comparable

DeepSeek-V3.1: —, GPT-4.1 nano: 29.2 (#113)

Multimodal benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
LMArena Vision	—	1063

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.6 (#106), GPT-4.1 nano: 41.6 (#205)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
LMArena Non-English	1400	1260
LMArena Chinese	1469	1270
LMArena German	1411	1288
LMArena Japanese	1378	1198
LMArena Russian	1405	1261
LMArena French	1447	—
LMArena Korean	1337	—
LMArena Spanish	1431	—

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 73.9 (#110), GPT-4.1 nano: 67.8 (#193)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
LMArena Instruction Following	1400	1267
IFEval	—	84.3%

Long Context DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.3 (#232), GPT-4.1 nano: 23.7 (#296)

Long Context benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
Fiction.LiveBench	52.8%	25%
LMArena Longer Query	1422	1283

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.3 (#98), GPT-4.1 nano: 40.5 (#243)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	GPT-4.1 nano
LMArena Text	1420	1285
LMArena Creative Writing	1401	1260
EQ-Bench Creative Writing	1436	946
LMArena Multi-Turn	1408	1277
WildBench	—	81.2%

Frequently asked questions

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

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

GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

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

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 24.1 in the Noometry coding category.

Which has the bigger context window?

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

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

21 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-4.1 nano has 38.