Noometry

Model comparison

Claude 3 Haiku vs Llama 3.1-8B

Claude 3 Haiku is the stronger model overall, scoring 25.7 to 22.8 on the Noometry Index.

Last verified . 30 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Llama 3.1-8B Meta

22.8

Rank #347 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude 3 Haiku scores higher in 6 categories and Llama 3.1-8B in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Haiku leads 17.3 to 8.0.
  • The biggest single-benchmark swing is BigCodeBench Complete: 50.1% for Claude 3 Haiku and 40.5% for Llama 3.1-8B.
  • Llama 3.1-8B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuLlama 3.1-8B
ProviderAnthropicMeta
Noometry Index25.722.8
Released2024-03-072024-07-23
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.08
Results tracked3743

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

Category by category

Coding Claude 3 Haiku leads

Claude 3 Haiku: 26.1 (#320), Llama 3.1-8B: 19.9 (#335)

BenchmarkClaude 3 HaikuLlama 3.1-8B
WeirdML9.8%1.7%
BigCodeBench Instruct39.4%32.8%
LMArena Coding11991195
BigCodeBench Complete50.1%40.5%
HumanEval+68.9%62.8%
MBPP+68.8%55.6%
SciCode—13.2%
CadEval12%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Llama 3.1-8B: 22.3 (#123)

BenchmarkClaude 3 HaikuLlama 3.1-8B
Berkeley Function Calling Leaderboard—25.8%
BALROG—15.1%

Reasoning Claude 3 Haiku leads

Claude 3 Haiku: 15.7 (#303), Llama 3.1-8B: 14.5 (#316)

BenchmarkClaude 3 HaikuLlama 3.1-8B
LMArena Hard Prompts11741175
DTBench50.1%50.9%
LMCA8.8%5.4%
Epoch Capabilities Index118.3116.48
Kagi LLM Benchmark34.2%—
CritPt—0%
Chess Puzzles—0%
ForecastBench53.2—
PIQA—81.2%
WinoGrande74.2%—

Math Too close to call

Claude 3 Haiku: 9.2 (#313), Llama 3.1-8B: 9.5 (#311)

BenchmarkClaude 3 HaikuLlama 3.1-8B
OTIS Mock AIME 2024-20251.8%1.7%
LMArena Math11881179
MATH Level 514.9%22.9%
Omni-MATH—13.7%
GSM8K—82.4%

Knowledge Claude 3 Haiku leads

Claude 3 Haiku: 17.3 (#280), Llama 3.1-8B: 8.0 (#302)

BenchmarkClaude 3 HaikuLlama 3.1-8B
GPQA Diamond36.3%27%
LMArena Expert11481144
MMLU73.8%56.1%
MMLU-Pro—40.6%
Confabulations34.2%—
GPQA (HELM)—24.7%
BoolQ—82.8%

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), Llama 3.1-8B: —

BenchmarkClaude 3 HaikuLlama 3.1-8B
LMArena Vision950—
ScienceQA72%—

Multilingual Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#238), Llama 3.1-8B: 34.2 (#244)

BenchmarkClaude 3 HaikuLlama 3.1-8B
LMArena Non-English11781148
LMArena Chinese11551151
LMArena French11941176
LMArena German11741144
LMArena Japanese11021061
LMArena Korean11081053
LMArena Russian12041158
LMArena Spanish11651169

Instruction Following Claude 3 Haiku leads

Claude 3 Haiku: 61.5 (#242), Llama 3.1-8B: 59.1 (#253)

BenchmarkClaude 3 HaikuLlama 3.1-8B
LMArena Instruction Following11741159
IFEval—74.3%

Long Context Too close to call

Claude 3 Haiku: 36.1 (#232), Llama 3.1-8B: 35.8 (#233)

BenchmarkClaude 3 HaikuLlama 3.1-8B
LMArena Longer Query11911182

Writing & Preference Too close to call

Claude 3 Haiku: 29.8 (#286), Llama 3.1-8B: 29.9 (#285)

BenchmarkClaude 3 HaikuLlama 3.1-8B
LMArena Text11951187
LMArena Creative Writing11571154
EQ-Bench Creative Writing717713
LMArena Multi-Turn11901172
WildBench—68.7%

Frequently asked questions

Is Claude 3 Haiku better than Llama 3.1-8B?

Claude 3 Haiku is the stronger model overall, scoring 25.7 to 22.8 on the Noometry Index.

Is Claude 3 Haiku or Llama 3.1-8B better for coding?

Claude 3 Haiku scores higher on coding benchmarks: 26.1 versus 19.9 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Llama 3.1-8B share?

30 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Llama 3.1-8B has 43.

Related comparisons

Go deeper