Noometry

Model comparison

Claude 3 Haiku vs Nemotron 4 340b Instruct

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 25.7 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Nemotron 4 340b Instruct NVIDIA

35.3

Rank #218 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Nemotron 4 340b Instruct in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Nemotron 4 340b Instruct leads 31.7 to 9.2.
  • Nemotron 4 340b Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuNemotron 4 340b Instruct
ProviderAnthropicNVIDIA
Noometry Index25.735.3
Released2024-03-072024-06-14
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3717

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

Category by category

Coding Nemotron 4 340b Instruct leads

Claude 3 Haiku: 26.1 (#320), Nemotron 4 340b Instruct: 34.6 (#223)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Coding11991209
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Nemotron 4 340b Instruct leads

Claude 3 Haiku: 15.7 (#303), Nemotron 4 340b Instruct: 22.4 (#180)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Hard Prompts11741202
Kagi LLM Benchmark34.2%—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.3—
ForecastBench53.2—
WinoGrande74.2%—

Math Nemotron 4 340b Instruct leads

Claude 3 Haiku: 9.2 (#313), Nemotron 4 340b Instruct: 31.7 (#193)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Math11881216
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge Nemotron 4 340b Instruct leads

Claude 3 Haiku: 17.3 (#280), Nemotron 4 340b Instruct: 31.4 (#212)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Expert11481171
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), Nemotron 4 340b Instruct: —

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Vision950—
ScienceQA72%—

Multilingual Nemotron 4 340b Instruct leads

Claude 3 Haiku: 36.1 (#238), Nemotron 4 340b Instruct: 38.0 (#228)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Non-English11781206
LMArena Chinese11551214
LMArena French11941196
LMArena German11741192
LMArena Japanese11021128
LMArena Korean11081148
LMArena Russian12041219
LMArena Spanish11651195

Instruction Following Nemotron 4 340b Instruct leads

Claude 3 Haiku: 61.5 (#242), Nemotron 4 340b Instruct: 63.3 (#227)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Instruction Following11741203

Long Context Nemotron 4 340b Instruct leads

Claude 3 Haiku: 36.1 (#232), Nemotron 4 340b Instruct: 37.1 (#216)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Longer Query11911225

Writing & Preference Nemotron 4 340b Instruct leads

Claude 3 Haiku: 29.8 (#286), Nemotron 4 340b Instruct: 42.9 (#229)

BenchmarkClaude 3 HaikuNemotron 4 340b Instruct
LMArena Text11951225
LMArena Creative Writing11571203
LMArena Multi-Turn11901214
EQ-Bench Creative Writing717—

Frequently asked questions

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

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 25.7 on the Noometry Index.

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

Nemotron 4 340b Instruct scores higher on coding benchmarks: 34.6 versus 26.1 in the Noometry coding category.

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

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Nemotron 4 340b Instruct has 17.

Related comparisons

Go deeper