Noometry

Model comparison

GPT-4.5 vs Llama 3-70B

GPT-4.5 is the stronger model overall, scoring 37.2 to 28.8 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-4.5 scores higher in 8 categories and Llama 3-70B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-4.5 leads 32.6 to 12.8.
  • The biggest single-benchmark swing is MATH Level 5: 78.6% for GPT-4.5 and 22.6% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Llama 3-70B
ProviderOpenAIMeta
Noometry Index37.228.8
Released2025-02-272024-04-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4231

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), Llama 3-70B: 35.8 (#218)

BenchmarkGPT-4.5Llama 3-70B
LMArena Coding13961206
Aider Polyglot44.9%—
WeirdML39.4%—
BigCodeBench Instruct—43.6%
LiveBench Coding75.2%—
BigCodeBench Complete—54.5%
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use GPT-4.5 leads

GPT-4.5: 27.9 (#97), Llama 3-70B: 21.1 (#139)

BenchmarkGPT-4.5Llama 3-70B
Cybench17.5%5%

Reasoning Llama 3-70B leads

GPT-4.5: 13.9 (#330), Llama 3-70B: 18.0 (#288)

BenchmarkGPT-4.5Llama 3-70B
LMArena Hard Prompts14031195
Epoch Capabilities Index136.74122.93
ForecastBench61.757.1
ARC-AGI-20.8%—
SimpleBench34.5%—
Kagi LLM Benchmark—35.1%
ARC-AGI-110.3%—
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
DTBench—54.2%
LiveBench Data Analysis64.3%—
LiveBench69%—
WinoGrande—83.5%

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), Llama 3-70B: 12.8 (#305)

BenchmarkGPT-4.5Llama 3-70B
OTIS Mock AIME 2024-202537.8%4.3%
LMArena Math14121218
MATH Level 578.6%22.6%
LiveBench Math69.3%—

Knowledge GPT-4.5 leads

GPT-4.5: 32.5 (#211), Llama 3-70B: 20.8 (#277)

BenchmarkGPT-4.5Llama 3-70B
GPQA Diamond68.7%40.6%
LMArena Expert13941149
Humanity's Last Exam5.4%—
Confabulations13.6%—
MMLU—79.3%

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Llama 3-70B: —

BenchmarkGPT-4.5Llama 3-70B
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), Llama 3-70B: 33.6 (#251)

BenchmarkGPT-4.5Llama 3-70B
LMArena Non-English14131142
LMArena Chinese14211114
LMArena French14181232
LMArena German14571169
LMArena Japanese14161017
LMArena Korean13921017
LMArena Russian14191159
LMArena Spanish—1241

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), Llama 3-70B: 62.5 (#238)

BenchmarkGPT-4.5Llama 3-70B
LMArena Instruction Following14041194
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Llama 3-70B: 35.6 (#240)

BenchmarkGPT-4.5Llama 3-70B
LMArena Longer Query14061174
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), Llama 3-70B: 42.8 (#231)

BenchmarkGPT-4.5Llama 3-70B
LMArena Text14171221
LMArena Creative Writing13941210
LMArena Multi-Turn14441223
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Llama 3-70B?

GPT-4.5 is the stronger model overall, scoring 37.2 to 28.8 on the Noometry Index.

Is GPT-4.5 or Llama 3-70B better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 35.8 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Llama 3-70B share?

22 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper