Model comparison

DeepSeek-V3.1 vs Nemotron 3 Ultra

DeepSeek-V3.1 and Nemotron 3 Ultra score almost the same on the Noometry Index (42.8 vs 42.5), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 21 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.8

Rank #108 Confirmed

Nemotron 3 Ultra

NVIDIA

42.5

Rank #113 Confirmed

Summary

They share 21 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 2 categories and Nemotron 3 Ultra in 6 categories; 7 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 43.7.
The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 36.9% for Nemotron 3 Ultra.
DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
Nemotron 3 Ultra accepts more context: 262K tokens versus 164K.

Side by side

DeepSeek-V3.1 and Nemotron 3 Ultra specifications
	DeepSeek-V3.1	Nemotron 3 Ultra
Provider	DeepSeek	NVIDIA
Noometry Index	42.8	42.5
Released	2025-08-21	2026-06-04
Weights	Open	Open
Context window	164K	262K
Max output	8K	128K
Input $ / M tokens	$0.25	$0.50
Output $ / M tokens	$0.95	$2.20
Results tracked	27	30

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), Nemotron 3 Ultra: 38.1 (#182)

Coding benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
WeirdML	38.4%	43.5%
LMArena Coding	1417	1468
FrontierCode	—	13.6%
SciCode	—	40.3%

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, Nemotron 3 Ultra: 23.4 (#126)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
APEX-Agents	—	22.7%

Reasoning Nemotron 3 Ultra leads

DeepSeek-V3.1: 27.9 (#110), Nemotron 3 Ultra: 31.0 (#82)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
LMArena Hard Prompts	1417	1452
DTBench	82.7%	90.1%
LMCA	24.3%	36.9%
Epoch Capabilities Index	139.92	146.17
SimpleBench	40%	—
Kagi LLM Benchmark	53.2%	—
CritPt	—	3.1%
Chess Puzzles	—	12%
Mystery Game Puzzles	—	20%
ForecastBench	58	—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 38.9 (#122), Nemotron 3 Ultra: 35.3 (#187)

Math benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
LMArena Math	1420	1457
OTIS Mock AIME 2024-2025	—	86.7%
ProofBench	—	2%

Knowledge Nemotron 3 Ultra leads

DeepSeek-V3.1: 43.7 (#90), Nemotron 3 Ultra: 52.5 (#61)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
LMArena Expert	1405	1472
GPQA Diamond	—	85.4%
Vectara Hallucination Rate	5.5%	—

Multilingual Nemotron 3 Ultra leads

DeepSeek-V3.1: 51.6 (#106), Nemotron 3 Ultra: 53.5 (#64)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
LMArena Non-English	1400	1427
LMArena Chinese	1469	1497
LMArena French	1447	1472
LMArena German	1411	1471
LMArena Korean	1337	1386
LMArena Russian	1405	1417
LMArena Spanish	1431	1454
LMArena Japanese	1378	—

Instruction Following Too close to call

DeepSeek-V3.1: 73.9 (#110), Nemotron 3 Ultra: 74.7 (#88)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
LMArena Instruction Following	1400	1418

Long Context Nemotron 3 Ultra leads

DeepSeek-V3.1: 36.3 (#232), Nemotron 3 Ultra: 43.9 (#81)

Long Context benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
LMArena Longer Query	1422	1437
Fiction.LiveBench	52.8%	—

Writing & Preference Nemotron 3 Ultra leads

DeepSeek-V3.1: 60.3 (#98), Nemotron 3 Ultra: 66.3 (#36)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	Nemotron 3 Ultra
LMArena Text	1420	1445
LMArena Creative Writing	1401	1398
EQ-Bench Creative Writing	1436	1692
LMArena Multi-Turn	1408	1411

Frequently asked questions

Is DeepSeek-V3.1 better than Nemotron 3 Ultra?

DeepSeek-V3.1 and Nemotron 3 Ultra score almost the same on the Noometry Index (42.8 vs 42.5), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek-V3.1 or Nemotron 3 Ultra?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.

Is DeepSeek-V3.1 or Nemotron 3 Ultra better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 38.1 in the Noometry coding category.

Which has the bigger context window?

Nemotron 3 Ultra does, with 262K tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and Nemotron 3 Ultra share?

21 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Nemotron 3 Ultra has 30.