Model comparison

Claude 3 Sonnet vs Nemotron 4 340b Instruct

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 28.8 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Sonnet Anthropic

28.8

Rank #311 Confirmed

Nemotron 4 340b Instruct NVIDIA

35.3

Rank #218 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Nemotron 4 340b Instruct in 8 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Nemotron 4 340b Instruct leads 31.7 to 10.0.
  • Nemotron 4 340b Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3 Sonnet and Nemotron 4 340b Instruct specifications
Claude 3 SonnetNemotron 4 340b Instruct
ProviderAnthropicNVIDIA
Noometry Index28.835.3
Released2024-02-292024-06-14
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3017

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

Category by category

Coding Nemotron 4 340b Instruct leads

Claude 3 Sonnet: 29.2 (#296), Nemotron 4 340b Instruct: 34.6 (#223)

Coding benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Coding12231209
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Nemotron 4 340b Instruct leads

Claude 3 Sonnet: 19.7 (#232), Nemotron 4 340b Instruct: 22.4 (#180)

Reasoning benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Hard Prompts11971202
DTBench53.6%—
Epoch Capabilities Index120.69—
WinoGrande75.1%—

Math Nemotron 4 340b Instruct leads

Claude 3 Sonnet: 10.0 (#305), Nemotron 4 340b Instruct: 31.7 (#193)

Math benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Math12131216
OTIS Mock AIME 2024-20252.5%—
MATH Level 518.2%—

Knowledge Nemotron 4 340b Instruct leads

Claude 3 Sonnet: 21.1 (#271), Nemotron 4 340b Instruct: 31.4 (#212)

Knowledge benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Expert11731171
GPQA Diamond40.6%—
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 24.7 (#120), Nemotron 4 340b Instruct: —

Multimodal benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Vision984—

Multilingual Too close to call

Claude 3 Sonnet: 38.0 (#229), Nemotron 4 340b Instruct: 38.0 (#228)

Multilingual benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Non-English12051206
LMArena Chinese11881214
LMArena French12281196
LMArena German12041192
LMArena Japanese11311128
LMArena Korean11281148
LMArena Russian12271219
LMArena Spanish12041195

Instruction Following Too close to call

Claude 3 Sonnet: 63.1 (#230), Nemotron 4 340b Instruct: 63.3 (#227)

Instruction Following benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Instruction Following12001203

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#223), Nemotron 4 340b Instruct: 37.1 (#216)

Long Context benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Longer Query12111225

Writing & Preference Too close to call

Claude 3 Sonnet: 42.3 (#233), Nemotron 4 340b Instruct: 42.9 (#229)

Writing & Preference benchmarks
BenchmarkClaude 3 SonnetNemotron 4 340b Instruct
LMArena Text12181225
LMArena Creative Writing11861203
LMArena Multi-Turn12271214

Frequently asked questions

Is Claude 3 Sonnet better than Nemotron 4 340b Instruct?

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 28.8 on the Noometry Index.

Is Claude 3 Sonnet or Nemotron 4 340b Instruct better for coding?

Nemotron 4 340b Instruct scores higher on coding benchmarks: 34.6 versus 29.2 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Nemotron 4 340b Instruct share?

17 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Nemotron 4 340b Instruct has 17.

Related comparisons

Go deeper