Noometry

Model comparison

Claude 3 Sonnet vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 29.0 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 21.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 86.7% for Nemotron 3 Ultra.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetNemotron 3 Ultra
ProviderAnthropicNVIDIA
Noometry Index29.042.5
Released2024-02-292026-06-04
WeightsProprietaryOpen
Context window—262K
Max output—128K
Input $ / M tokens—$0.50
Output $ / M tokens—$2.20
Results tracked3030

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

Category by category

Coding Nemotron 3 Ultra leads

Claude 3 Sonnet: 29.6 (#302), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
WeirdML10.2%43.5%
LMArena Coding12231468
FrontierCode—13.6%
SciCode—40.3%
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Nemotron 3 Ultra: 23.4 (#126)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
APEX-Agents—22.7%

Reasoning Nemotron 3 Ultra leads

Claude 3 Sonnet: 20.5 (#237), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
LMArena Hard Prompts11971452
DTBench53.6%90.1%
Epoch Capabilities Index120.7146.17
CritPt—3.1%
Chess Puzzles—12%
Mystery Game Puzzles—20%
LMCA—36.9%
WinoGrande75.1%—

Math Nemotron 3 Ultra leads

Claude 3 Sonnet: 10.7 (#310), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
OTIS Mock AIME 2024-20252.5%86.7%
LMArena Math12131457
ProofBench—2%
MATH Level 518.2%—

Knowledge Nemotron 3 Ultra leads

Claude 3 Sonnet: 21.1 (#276), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
GPQA Diamond40.6%85.4%
LMArena Expert11731472
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Nemotron 3 Ultra: —

BenchmarkClaude 3 SonnetNemotron 3 Ultra
LMArena Vision984—

Multilingual Nemotron 3 Ultra leads

Claude 3 Sonnet: 37.8 (#234), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
LMArena Non-English12051427
LMArena Chinese11891497
LMArena French12291472
LMArena German12041471
LMArena Korean11281386
LMArena Russian12271417
LMArena Spanish12041454
LMArena Japanese1131—

Instruction Following Nemotron 3 Ultra leads

Claude 3 Sonnet: 62.8 (#235), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
LMArena Instruction Following11991418

Long Context Nemotron 3 Ultra leads

Claude 3 Sonnet: 36.7 (#228), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
LMArena Longer Query12111437

Writing & Preference Nemotron 3 Ultra leads

Claude 3 Sonnet: 42.1 (#238), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkClaude 3 SonnetNemotron 3 Ultra
LMArena Text12181445
LMArena Creative Writing11861398
LMArena Multi-Turn12271411
EQ-Bench Creative Writing—1692

Frequently asked questions

Is Claude 3 Sonnet better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Nemotron 3 Ultra better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Nemotron 3 Ultra share?

21 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper