Noometry

Model comparison

GPT-5.4 mini vs Llama 3-70B

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 28.8 on the Noometry Index.

Last verified . 23 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.4 mini leads 45.5 to 12.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for GPT-5.4 mini and 4.3% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniLlama 3-70B
ProviderOpenAIMeta
Noometry Index45.028.8
Released2026-03-172024-04-18
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4631

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.2 (#72), Llama 3-70B: 35.8 (#218)

BenchmarkGPT-5.4 miniLlama 3-70B
LMArena Coding14381206
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
ALE-Bench1,189—
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use GPT-5.4 mini leads

GPT-5.4 mini: 29.9 (#81), Llama 3-70B: 21.1 (#139)

BenchmarkGPT-5.4 miniLlama 3-70B
Cybench—5%
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Llama 3-70B: 18.0 (#288)

BenchmarkGPT-5.4 miniLlama 3-70B
Kagi LLM Benchmark37.9%35.1%
LMArena Hard Prompts14241195
DTBench80%54.2%
Epoch Capabilities Index148.84122.93
ForecastBench5757.1
ARC-AGI-218.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Chess Puzzles24%—
Thematic Generalization61.7%—
Mystery Game Puzzles11%—
LMCA40.8%—
WinoGrande—83.5%

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), Llama 3-70B: 12.8 (#305)

BenchmarkGPT-5.4 miniLlama 3-70B
OTIS Mock AIME 2024-202588.9%4.3%
LMArena Math14191218
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
ProofBench21%—
MATH Level 5—22.6%
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.5 (#67), Llama 3-70B: 20.8 (#277)

BenchmarkGPT-5.4 miniLlama 3-70B
GPQA Diamond86.9%40.6%
LMArena Expert14351149
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—
MMLU—79.3%

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), Llama 3-70B: —

BenchmarkGPT-5.4 miniLlama 3-70B
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 51.9 (#96), Llama 3-70B: 33.6 (#251)

BenchmarkGPT-5.4 miniLlama 3-70B
LMArena Non-English14051142
LMArena Chinese14461114
LMArena French14401232
LMArena German14091169
LMArena Japanese13741017
LMArena Korean13681017
LMArena Russian14171159
LMArena Spanish14051241

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.1 (#102), Llama 3-70B: 62.5 (#238)

BenchmarkGPT-5.4 miniLlama 3-70B
LMArena Instruction Following14051194

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 43.0 (#112), Llama 3-70B: 35.6 (#240)

BenchmarkGPT-5.4 miniLlama 3-70B
LMArena Longer Query14071174

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), Llama 3-70B: 42.8 (#231)

BenchmarkGPT-5.4 miniLlama 3-70B
LMArena Text14121221
LMArena Creative Writing13701210
LMArena Multi-Turn14291223
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Llama 3-70B?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 28.8 on the Noometry Index.

Is GPT-5.4 mini or Llama 3-70B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 35.8 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and Llama 3-70B share?

23 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper