Model comparison

DeepSeek-V3.1-Terminus vs GPT-5.3 Codex

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 11× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Last verified October 10, 2026. 1 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

43.1

Rank #97 Confirmed

GPT-5.3 Codex OpenAI

45.8

Rank #69 Reported

Summary

They share 1 benchmark with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and GPT-5.3 Codex in 1 category; one gap is clear of the uncertainty.
The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 42.0.
DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
GPT-5.3 Codex accepts more context: 400K tokens versus 164K.
DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1-Terminus and GPT-5.3 Codex specifications
	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
Provider	DeepSeek	OpenAI
Noometry Index	43.1	45.8
Released	2025-09-22	2026-02-05
Weights	Open	Proprietary
Context window	164K	400K
Max output	147K	128K
Input $ / M tokens	$0.27	$1.75
Output $ / M tokens	$1	$14
Results tracked	16	8

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

Category by category

Coding GPT-5.3 Codex leads

DeepSeek-V3.1-Terminus: 42.0 (#113), GPT-5.3 Codex: 48.6 (#56)

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
ALE-Bench	745.17	1,655
SWE-bench Verified	—	74.8%
LMArena WebDev	—	1409
SciCode	40.6%	—
WeirdML	—	79.3%
LMArena Coding	1426	—

Agentic & Tool Use Not comparable

DeepSeek-V3.1-Terminus: —, GPT-5.3 Codex: 48.0 (#9)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
Terminal-Bench	—	78.4%
METR Time Horizons	—	74.5%
Vending-Bench 2	—	5,940

Reasoning Not comparable

DeepSeek-V3.1-Terminus: 26.4 (#133), GPT-5.3 Codex: —

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
Kagi LLM Benchmark	57.4%	—
CritPt	1.7%	—
LMArena Hard Prompts	1426	—
DTBench	81.3%	—
LMCA	28.6%	—
Epoch Capabilities Index	—	156.77

Math Not comparable

DeepSeek-V3.1-Terminus: 38.5 (#137), GPT-5.3 Codex: —

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
LMArena Math	1402	—

Multilingual Not comparable

DeepSeek-V3.1-Terminus: 52.1 (#92), GPT-5.3 Codex: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
LMArena Non-English	1407	—
LMArena Russian	1436	—

Instruction Following Not comparable

DeepSeek-V3.1-Terminus: 74.0 (#106), GPT-5.3 Codex: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
LMArena Instruction Following	1404	—

Long Context Not comparable

DeepSeek-V3.1-Terminus: 43.4 (#97), GPT-5.3 Codex: —

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
LMArena Longer Query	1421	—

Writing & Preference Not comparable

DeepSeek-V3.1-Terminus: 61.0 (#92), GPT-5.3 Codex: —

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-5.3 Codex
LMArena Text	1419	—
LMArena Creative Writing	1403	—
LMArena Multi-Turn	1411	—

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than GPT-5.3 Codex?

Which is cheaper, DeepSeek-V3.1-Terminus or GPT-5.3 Codex?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

Is DeepSeek-V3.1-Terminus or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 42.0 in the Noometry coding category.

Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 164K.

How many benchmarks do DeepSeek-V3.1-Terminus and GPT-5.3 Codex share?

1 benchmark has published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GPT-5.3 Codex has 8.