Noometry

Model comparison

Claude 3.5 Haiku vs Nemotron 4 340b Instruct

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 29.2 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Nemotron 4 340b Instruct NVIDIA

35.9

Rank #223 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 2 categories and Nemotron 4 340b Instruct in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Nemotron 4 340b Instruct leads 34.3 to 14.7.
  • Nemotron 4 340b Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuNemotron 4 340b Instruct
ProviderAnthropicNVIDIA
Noometry Index29.235.9
Released2024-10-222024-06-14
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4917

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

Category by category

Coding Nemotron 4 340b Instruct leads

Claude 3.5 Haiku: 32.9 (#265), Nemotron 4 340b Instruct: 35.2 (#228)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Coding12861209
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Nemotron 4 340b Instruct: —

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
BALROG19.3%—

Reasoning Nemotron 4 340b Instruct leads

Claude 3.5 Haiku: 17.7 (#290), Nemotron 4 340b Instruct: 23.4 (#178)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Hard Prompts12511202
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Nemotron 4 340b Instruct leads

Claude 3.5 Haiku: 14.7 (#300), Nemotron 4 340b Instruct: 34.3 (#195)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Math12441216
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Nemotron 4 340b Instruct leads

Claude 3.5 Haiku: 18.7 (#281), Nemotron 4 340b Instruct: 32.0 (#216)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Expert12081171
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Nemotron 4 340b Instruct: —

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Vision1092—
GeoBench34%—

Multilingual Claude 3.5 Haiku leads

Claude 3.5 Haiku: 40.0 (#218), Nemotron 4 340b Instruct: 37.9 (#233)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Non-English12381206
LMArena Chinese12291214
LMArena French12641197
LMArena German12371192
LMArena Japanese11751128
LMArena Korean11731148
LMArena Russian12531219
LMArena Spanish12611195

Instruction Following Too close to call

Claude 3.5 Haiku: 62.9 (#234), Nemotron 4 340b Instruct: 63.1 (#232)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Instruction Following12411203
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Claude 3.5 Haiku leads

Claude 3.5 Haiku: 38.3 (#200), Nemotron 4 340b Instruct: 37.1 (#221)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Longer Query12611225

Writing & Preference Too close to call

Claude 3.5 Haiku: 42.7 (#234), Nemotron 4 340b Instruct: 42.7 (#233)

BenchmarkClaude 3.5 HaikuNemotron 4 340b Instruct
LMArena Text12551225
LMArena Creative Writing12331203
LMArena Multi-Turn12651214
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Nemotron 4 340b Instruct?

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Nemotron 4 340b Instruct better for coding?

Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Nemotron 4 340b Instruct share?

17 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Nemotron 4 340b Instruct has 17.

Related comparisons

Go deeper