Model comparison

DeepSeek-V3.1 vs GPT-5 Pro

GPT-5 Pro is the stronger model overall, scoring 46.4 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 97× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.

Last verified October 10, 2026. 4 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.8

Rank #108 Confirmed

GPT-5 Pro OpenAI

46.4

Rank #64 Confirmed

Summary

They share 4 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 0 categories and GPT-5 Pro in 4 categories; 4 gaps are clear of the uncertainty.
The widest gap is in knowledge, where GPT-5 Pro leads 56.7 to 43.7.
The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for DeepSeek-V3.1 and 76.8% for GPT-5 Pro.
DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
GPT-5 Pro accepts more context: 400K tokens versus 164K.
DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1 and GPT-5 Pro specifications
	DeepSeek-V3.1	GPT-5 Pro
Provider	DeepSeek	OpenAI
Noometry Index	42.8	46.4
Released	2025-08-21	2025-10-06
Weights	Open	Proprietary
Context window	164K	400K
Max output	8K	272K
Input $ / M tokens	$0.25	$15
Output $ / M tokens	$0.95	$120
Results tracked	27	12

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

Category by category

Coding GPT-5 Pro leads

DeepSeek-V3.1: 40.3 (#144), GPT-5 Pro: 44.0 (#80)

Coding benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
WeirdML	38.4%	60.4%
LMArena Coding	1417	—
AlgoTune	—	1.31

Reasoning GPT-5 Pro leads

DeepSeek-V3.1: 27.9 (#110), GPT-5 Pro: 38.9 (#62)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
SimpleBench	40%	61.6%
Kagi LLM Benchmark	53.2%	76.8%
Epoch Capabilities Index	139.92	150.28
ARC-AGI-2	—	18.3%
ARC-AGI-1	—	70.2%
EnigmaEval	—	18.8%
LMArena Hard Prompts	1417	—
DTBench	82.7%	—
LMCA	24.3%	—
ForecastBench	58	—

Math GPT-5 Pro leads

DeepSeek-V3.1: 38.9 (#122), GPT-5 Pro: 48.5 (#63)

Math benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
FrontierMath (Tiers 1-3)	—	55.8%
FrontierMath Tier 4	—	19.5%
LMArena Math	1420	—
FrontierMath Tier 4 (v1)	—	14.6%

Knowledge GPT-5 Pro leads

DeepSeek-V3.1: 43.7 (#90), GPT-5 Pro: 56.7 (#42)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
Humanity's Last Exam	—	31.6%
Vectara Hallucination Rate	5.5%	—
LMArena Expert	1405	—

Multilingual Not comparable

DeepSeek-V3.1: 51.6 (#106), GPT-5 Pro: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
LMArena Non-English	1400	—
LMArena Chinese	1469	—
LMArena French	1447	—
LMArena German	1411	—
LMArena Japanese	1378	—
LMArena Korean	1337	—
LMArena Russian	1405	—
LMArena Spanish	1431	—

Instruction Following Not comparable

DeepSeek-V3.1: 73.9 (#110), GPT-5 Pro: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
LMArena Instruction Following	1400	—

Long Context Not comparable

DeepSeek-V3.1: 36.3 (#232), GPT-5 Pro: —

Long Context benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
Fiction.LiveBench	52.8%	—
LMArena Longer Query	1422	—

Writing & Preference Not comparable

DeepSeek-V3.1: 60.3 (#98), GPT-5 Pro: —

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	GPT-5 Pro
LMArena Text	1420	—
LMArena Creative Writing	1401	—
EQ-Bench Creative Writing	1436	—
LMArena Multi-Turn	1408	—

Frequently asked questions

Is DeepSeek-V3.1 better than GPT-5 Pro?

Which is cheaper, DeepSeek-V3.1 or GPT-5 Pro?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GPT-5 Pro lists at $15 and $120.

Is DeepSeek-V3.1 or GPT-5 Pro better for coding?

GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 40.3 in the Noometry coding category.

Which has the bigger context window?

GPT-5 Pro does, with 400K tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and GPT-5 Pro share?

4 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-5 Pro has 12.