Noometry

Model comparison

GPT-4.5 vs Llama 3-8B

GPT-4.5 is the stronger model overall, scoring 36.9 to 25.3 on the Noometry Index.

Last verified . 21 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Llama 3-8B Meta

25.3

Rank #338 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-4.5 scores higher in 8 categories and Llama 3-8B in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.5 leads 32.4 to 7.8.
  • The biggest single-benchmark swing is MATH Level 5: 78.6% for GPT-4.5 and 6.1% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Llama 3-8B
ProviderOpenAIMeta
Noometry Index36.925.3
Released2025-02-272024-04-18
WeightsProprietaryOpen
Context window—8K
Max output—8K
Input $ / M tokens—$0.14
Output $ / M tokens—$0.14
Results tracked4234

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 41.8 (#102), Llama 3-8B: 30.5 (#285)

BenchmarkGPT-4.5Llama 3-8B
LMArena Coding13971152
Aider Polyglot44.9%—
WeirdML39.4%—
BigCodeBench Instruct—31.9%
LiveBench Coding75.2%—
BigCodeBench Complete—36.9%
HumanEval+—56.7%
MBPP+—54.8%

Agentic & Tool Use Not comparable

GPT-4.5: 27.6 (#92), Llama 3-8B: —

BenchmarkGPT-4.5Llama 3-8B
Cybench17.5%—

Reasoning Too close to call

GPT-4.5: 14.1 (#320), Llama 3-8B: 13.8 (#321)

BenchmarkGPT-4.5Llama 3-8B
LMArena Hard Prompts14041133
Epoch Capabilities Index136.74116.33
ForecastBench61.758.6
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
Chess Puzzles—0%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
DTBench—43.9%
LiveBench Data Analysis64.3%—
Adversarial NLI—57.3%
LiveBench69%—
WinoGrande—75.7%

Math GPT-4.5 leads

GPT-4.5: 31.0 (#200), Llama 3-8B: 8.3 (#317)

BenchmarkGPT-4.5Llama 3-8B
OTIS Mock AIME 2024-202537.8%1.9%
LMArena Math14121151
MATH Level 578.6%6.1%
LiveBench Math69.3%—

Knowledge GPT-4.5 leads

GPT-4.5: 32.4 (#205), Llama 3-8B: 7.8 (#303)

BenchmarkGPT-4.5Llama 3-8B
GPQA Diamond68.7%26.1%
LMArena Expert13941113
Humanity's Last Exam5.4%—
Confabulations13.6%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multimodal Not comparable

GPT-4.5: 37.0 (#68), Llama 3-8B: —

BenchmarkGPT-4.5Llama 3-8B
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.7 (#78), Llama 3-8B: 31.0 (#256)

BenchmarkGPT-4.5Llama 3-8B
LMArena Non-English14131098
LMArena Chinese14211076
LMArena French14171158
LMArena German14571104
LMArena Japanese1416967
LMArena Korean13921003
LMArena Russian14191109
LMArena Spanish—1172

Instruction Following GPT-4.5 leads

GPT-4.5: 72.8 (#129), Llama 3-8B: 58.7 (#255)

BenchmarkGPT-4.5Llama 3-8B
LMArena Instruction Following14041127
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#150), Llama 3-8B: 34.2 (#246)

BenchmarkGPT-4.5Llama 3-8B
LMArena Longer Query14061128
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 57.1 (#129), Llama 3-8B: 37.7 (#251)

BenchmarkGPT-4.5Llama 3-8B
LMArena Text14171166
LMArena Creative Writing13941150
LMArena Multi-Turn14441152
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Llama 3-8B?

GPT-4.5 is the stronger model overall, scoring 36.9 to 25.3 on the Noometry Index.

Is GPT-4.5 or Llama 3-8B better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 30.5 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Llama 3-8B share?

21 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper