Model comparison

DeepSeek Coder 33B vs Nemotron 3 Super

Nemotron 3 Super has enough public results to be ranked (#147); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

DeepSeek Coder 33B DeepSeek

38.3

Unranked Sparse

Nemotron 3 Super NVIDIA

39.6

Rank #147 Confirmed

Side by side

DeepSeek Coder 33B and Nemotron 3 Super specifications
DeepSeek Coder 33BNemotron 3 Super
ProviderDeepSeekNVIDIA
Noometry Index38.339.6
Released2023-11-022026-03-11
WeightsOpenOpen
Context window—262K
Max output—131K
Input $ / M tokens—$0.08
Output $ / M tokens—$0.45
Results tracked921

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

Category by category

Coding Nemotron 3 Super leads

DeepSeek Coder 33B: 37.4 (#180), Nemotron 3 Super: 38.9 (#153)

Coding benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
SciCode—36%
WeirdML—38%
BigCodeBench Instruct42%—
LMArena Coding—1403
BigCodeBench Complete51.1%—
ALE-Bench—213.9
HumanEval+75%—
MBPP+70.1%—

Reasoning Not comparable

DeepSeek Coder 33B: —, Nemotron 3 Super: 17.9 (#274)

Reasoning benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
NYT Connections (extended)—15.4%
CritPt—3.1%
LMArena Hard Prompts—1386
Epoch Capabilities Index95.74—
WinoGrande62%—

Math Not comparable

DeepSeek Coder 33B: —, Nemotron 3 Super: 37.6 (#95)

Math benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
MathArena Final-Answer Competitions—60.4%
LMArena Math—1381
GSM8K35.4%—

Knowledge Not comparable

DeepSeek Coder 33B: —, Nemotron 3 Super: 38.2 (#136)

Knowledge benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
LMArena Expert—1397
ARC (AI2) Challenge42.2%—
MMLU39.4%—

Multilingual Not comparable

DeepSeek Coder 33B: —, Nemotron 3 Super: 48.6 (#139)

Multilingual benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
LMArena Non-English—1356
LMArena Chinese—1430
LMArena French—1404
LMArena German—1341
LMArena Russian—1336
LMArena Spanish—1417

Instruction Following Not comparable

DeepSeek Coder 33B: —, Nemotron 3 Super: 71.4 (#149)

Instruction Following benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
LMArena Instruction Following—1347

Long Context Not comparable

DeepSeek Coder 33B: —, Nemotron 3 Super: 41.5 (#134)

Long Context benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
LMArena Longer Query—1362

Writing & Preference Not comparable

DeepSeek Coder 33B: —, Nemotron 3 Super: 56.1 (#135)

Writing & Preference benchmarks
BenchmarkDeepSeek Coder 33BNemotron 3 Super
LMArena Text—1378
LMArena Creative Writing—1317
LMArena Multi-Turn—1369

Frequently asked questions

Is DeepSeek Coder 33B better than Nemotron 3 Super?

Nemotron 3 Super has enough public results to be ranked (#147); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 33B or Nemotron 3 Super better for coding?

Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 37.4 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 33B and Nemotron 3 Super share?

0 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Nemotron 3 Super has 21.

Related comparisons

Go deeper