Noometry

Model comparison

Claude 3 Haiku vs Llama 3-70B

Llama 3-70B is the stronger model overall, scoring 28.5 to 25.7 on the Noometry Index.

Last verified . 30 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Llama 3-70B Meta

28.5

Rank #317 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude 3 Haiku scores higher in 2 categories and Llama 3-70B in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Llama 3-70B leads 43.0 to 29.8.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 22.6% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuLlama 3-70B
ProviderAnthropicMeta
Noometry Index25.728.5
Released2024-03-072024-04-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3731

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

Category by category

Coding Llama 3-70B leads

Claude 3 Haiku: 26.1 (#320), Llama 3-70B: 35.3 (#215)

BenchmarkClaude 3 HaikuLlama 3-70B
BigCodeBench Instruct39.4%43.6%
LMArena Coding11991206
BigCodeBench Complete50.1%54.5%
HumanEval+68.9%72%
MBPP+68.8%69%
WeirdML9.8%—
CadEval12%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Llama 3-70B: 20.9 (#132)

BenchmarkClaude 3 HaikuLlama 3-70B
Cybench—5%

Reasoning Llama 3-70B leads

Claude 3 Haiku: 15.7 (#303), Llama 3-70B: 17.4 (#284)

BenchmarkClaude 3 HaikuLlama 3-70B
Kagi LLM Benchmark34.2%35.1%
LMArena Hard Prompts11741195
DTBench50.1%54.2%
Epoch Capabilities Index118.3122.91
ForecastBench53.257.1
WinoGrande74.2%83.5%
LMCA8.8%—

Math Llama 3-70B leads

Claude 3 Haiku: 9.2 (#313), Llama 3-70B: 12.0 (#299)

BenchmarkClaude 3 HaikuLlama 3-70B
OTIS Mock AIME 2024-20251.8%4.3%
LMArena Math11881218
MATH Level 514.9%22.6%

Knowledge Llama 3-70B leads

Claude 3 Haiku: 17.3 (#280), Llama 3-70B: 20.8 (#272)

BenchmarkClaude 3 HaikuLlama 3-70B
GPQA Diamond36.3%40.6%
LMArena Expert11481149
MMLU73.8%79.3%
Confabulations34.2%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), Llama 3-70B: —

BenchmarkClaude 3 HaikuLlama 3-70B
LMArena Vision950—
ScienceQA72%—

Multilingual Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#238), Llama 3-70B: 33.8 (#246)

BenchmarkClaude 3 HaikuLlama 3-70B
LMArena Non-English11781142
LMArena Chinese11551114
LMArena French11941231
LMArena German11741169
LMArena Japanese11021017
LMArena Korean11081017
LMArena Russian12041159
LMArena Spanish11651241

Instruction Following Llama 3-70B leads

Claude 3 Haiku: 61.5 (#242), Llama 3-70B: 62.8 (#233)

BenchmarkClaude 3 HaikuLlama 3-70B
LMArena Instruction Following11741194

Long Context Too close to call

Claude 3 Haiku: 36.1 (#232), Llama 3-70B: 35.6 (#235)

BenchmarkClaude 3 HaikuLlama 3-70B
LMArena Longer Query11911174

Writing & Preference Llama 3-70B leads

Claude 3 Haiku: 29.8 (#286), Llama 3-70B: 43.0 (#225)

BenchmarkClaude 3 HaikuLlama 3-70B
LMArena Text11951221
LMArena Creative Writing11571210
LMArena Multi-Turn11901223
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Llama 3-70B?

Llama 3-70B is the stronger model overall, scoring 28.5 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or Llama 3-70B better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.3 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Llama 3-70B share?

30 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper