Model comparison

DeepSeek-R1 vs DeepSeek-V3.2-Speciale

DeepSeek-R1 is the stronger model overall, scoring 42.0 to 39.1 on the Noometry Index.

Last verified October 10, 2026. 3 shared benchmarks.

DeepSeek-R1

DeepSeek

42.0

Rank #110 Confirmed

DeepSeek-V3.2-Speciale

DeepSeek

39.1

Rank #159 Reported

Summary

They share 3 benchmarks with published results for both. DeepSeek-R1 scores higher in 2 categories and DeepSeek-V3.2-Speciale in 1 category; 3 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where DeepSeek-R1 leads 61.5 to 46.1.
The biggest single-benchmark swing is SimpleBench: 40.8% for DeepSeek-R1 and 52.6% for DeepSeek-V3.2-Speciale.
DeepSeek-V3.2-Speciale is cheaper at $0.58 / $1.68 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
DeepSeek-R1 accepts more context: 164K tokens versus 128K.
DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.

Side by side

DeepSeek-R1 and DeepSeek-V3.2-Speciale specifications
	DeepSeek-R1	DeepSeek-V3.2-Speciale
Provider	DeepSeek	DeepSeek
Noometry Index	42.0	39.1
Released	2025-01-20	2025-12-01
Weights	Proprietary	Open
Context window	164K	128K
Max output	64K	128K
Input $ / M tokens	$0.50	$0.58
Output $ / M tokens	$2.15	$1.68
Results tracked	52	3

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

Category by category

Coding DeepSeek-R1 leads

DeepSeek-R1: 45.9 (#63), DeepSeek-V3.2-Speciale: 39.9 (#136)

Coding benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
WeirdML	41.6%	46.7%
Aider Polyglot	71.4%	—
SciCode	35.7%	—
LiveBench Coding	66.7%	—
LMArena Coding	1427	—
ALE-Bench	804.12	—
AlgoTune	1.7	—

Agentic & Tool Use Not comparable

DeepSeek-R1: 30.4 (#68), DeepSeek-V3.2-Speciale: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
DeepResearch Bench	35.1%	—
BALROG	34.9%	—
METR Time Horizons	53.8%	—

Reasoning DeepSeek-V3.2-Speciale leads

DeepSeek-R1: 18.7 (#253), DeepSeek-V3.2-Speciale: 32.1 (#65)

Reasoning benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
SimpleBench	40.8%	52.6%
ARC-AGI-2	1.3%	—
Kagi LLM Benchmark	69.4%	—
ARC-AGI-1	21.2%	—
CritPt	1.1%	—
LiveBench Reasoning	83.2%	—
LMArena Hard Prompts	1415	—
LiveBench Data Analysis	69.8%	—
Epoch Capabilities Index	141.3	—
ForecastBench	60	—
LiveBench	71.6%	—

Math Not comparable

DeepSeek-R1: 42.0 (#70), DeepSeek-V3.2-Speciale: —

Math benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
OTIS Mock AIME 2024-2025	66.4%	—
Omni-MATH	42.4%	—
LiveBench Math	80.7%	—
LMArena Math	1401	—
MATH Level 5	96.6%	—

Knowledge Not comparable

DeepSeek-R1: 44.3 (#81), DeepSeek-V3.2-Speciale: —

Knowledge benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
GPQA Diamond	76.3%	—
MMLU-Pro	79.3%	—
Confabulations	12.7%	—
Vectara Hallucination Rate	11.3%	—
GPQA (HELM)	66.6%	—
LMArena Expert	1394	—

Multilingual Not comparable

DeepSeek-R1: 52.6 (#80), DeepSeek-V3.2-Speciale: —

Multilingual benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
LMArena Non-English	1412	—
LMArena Chinese	1443	—
LMArena French	1415	—
LMArena German	1405	—
LMArena Japanese	1394	—
LMArena Korean	1359	—
LMArena Russian	1423	—
LMArena Spanish	1410	—

Instruction Following Not comparable

DeepSeek-R1: 72.2 (#138), DeepSeek-V3.2-Speciale: —

Instruction Following benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
LiveBench Instruction Following	80.5%	—
IFEval	78.4%	—
LMArena Instruction Following	1382	—

Long Context Not comparable

DeepSeek-R1: 45.4 (#36), DeepSeek-V3.2-Speciale: —

Long Context benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
Fiction.LiveBench	75%	—
LMArena Longer Query	1391	—

Writing & Preference DeepSeek-R1 leads

DeepSeek-R1: 61.5 (#84), DeepSeek-V3.2-Speciale: 46.1 (#217)

Writing & Preference benchmarks
Benchmark	DeepSeek-R1	DeepSeek-V3.2-Speciale
EQ-Bench Creative Writing	1500	1276
LMArena Text	1428	—
LMArena Creative Writing	1406	—
Short-Story Creative Writing	83%	—
WildBench	82.8%	—
LMArena Multi-Turn	1404	—
LiveBench Language	48.5%	—

Frequently asked questions

Is DeepSeek-R1 better than DeepSeek-V3.2-Speciale?

DeepSeek-R1 is the stronger model overall, scoring 42.0 to 39.1 on the Noometry Index.

Which is cheaper, DeepSeek-R1 or DeepSeek-V3.2-Speciale?

DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.

Is DeepSeek-R1 or DeepSeek-V3.2-Speciale better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 39.9 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-R1 does, with 164K tokens against 128K.

How many benchmarks do DeepSeek-R1 and DeepSeek-V3.2-Speciale share?

3 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.