Model comparison

DeepSeek-V3.1-Terminus vs Nemotron 3 Super

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 39.6 on the Noometry Index. Nemotron 3 Super costs 2.8× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

Last verified October 10, 2026. 13 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

42.6

Rank #96 Confirmed

Nemotron 3 Super

NVIDIA

39.6

Rank #147 Confirmed

Summary

They share 13 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and Nemotron 3 Super in 1 category; 7 gaps are clear of the uncertainty.
The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 25.7 to 17.9.
Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
Nemotron 3 Super accepts more context: 262K tokens versus 164K.

Side by side

DeepSeek-V3.1-Terminus and Nemotron 3 Super specifications
	DeepSeek-V3.1-Terminus	Nemotron 3 Super
Provider	DeepSeek	NVIDIA
Noometry Index	42.6	39.6
Released	2025-09-22	2026-03-11
Weights	Open	Open
Context window	164K	262K
Max output	66K	131K
Input $ / M tokens	$0.30	$0.08
Output $ / M tokens	$1	$0.45
Results tracked	16	21

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

Category by category

Coding DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 41.5 (#114), Nemotron 3 Super: 38.9 (#153)

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
SciCode	40.6%	36%
LMArena Coding	1426	1403
ALE-Bench	745.17	213.9
WeirdML	—	38%

Reasoning DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 25.7 (#126), Nemotron 3 Super: 17.9 (#274)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
CritPt	1.7%	3.1%
LMArena Hard Prompts	1427	1386
Kagi LLM Benchmark	57.4%	—
NYT Connections (extended)	—	15.4%
DTBench	81.3%	—
LMCA	28.6%	—

Math Nemotron 3 Super leads

DeepSeek-V3.1-Terminus: 35.7 (#138), Nemotron 3 Super: 37.6 (#95)

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
LMArena Math	1402	1381
MathArena Final-Answer Competitions	—	60.4%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Nemotron 3 Super: 38.2 (#136)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
LMArena Expert	—	1397

Multilingual DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 52.3 (#87), Nemotron 3 Super: 48.6 (#139)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
LMArena Non-English	1407	1356
LMArena Russian	1434	1336
LMArena Chinese	—	1430
LMArena French	—	1404
LMArena German	—	1341
LMArena Spanish	—	1417

Instruction Following DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 74.4 (#96), Nemotron 3 Super: 71.4 (#149)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
LMArena Instruction Following	1406	1347

Long Context DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 43.5 (#88), Nemotron 3 Super: 41.5 (#134)

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
LMArena Longer Query	1426	1362

Writing & Preference DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 61.3 (#87), Nemotron 3 Super: 56.1 (#135)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Nemotron 3 Super
LMArena Text	1420	1378
LMArena Creative Writing	1404	1317
LMArena Multi-Turn	1411	1369

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Nemotron 3 Super?

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

Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.

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

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

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

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

13 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Nemotron 3 Super has 21.