Noometry

Model comparison

GPT-4.1 vs Llama 3-70B

GPT-4.1 is the stronger model overall, scoring 35.7 to 28.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-4.1 OpenAI

35.7

Rank #215 Confirmed

Llama 3-70B Meta

28.5

Rank #317 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-4.1 scores higher in 7 categories and Llama 3-70B in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 leads 37.0 to 20.8.
  • The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 22.6% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1Llama 3-70B
ProviderOpenAIMeta
Noometry Index35.728.5
Released2025-04-142024-04-18
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$2—
Output $ / M tokens$8—
Results tracked5231

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

Category by category

Coding Llama 3-70B leads

GPT-4.1: 34.2 (#228), Llama 3-70B: 35.3 (#215)

BenchmarkGPT-4.1Llama 3-70B
LMArena Coding13911206
SWE-bench Verified48.5%—
SWE-bench Verified (bash only)39.6%—
Aider Polyglot52.4%—
WeirdML39%—
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
CadEval42%—
ALE-Bench558.1—
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use GPT-4.1 leads

GPT-4.1: 34.4 (#40), Llama 3-70B: 20.9 (#132)

BenchmarkGPT-4.1Llama 3-70B
Berkeley Function Calling Leaderboard54%—
Cybench—5%

Reasoning Llama 3-70B leads

GPT-4.1: 11.7 (#334), Llama 3-70B: 17.4 (#284)

BenchmarkGPT-4.1Llama 3-70B
Kagi LLM Benchmark52.3%35.1%
LMArena Hard Prompts13841195
DTBench68.3%54.2%
Epoch Capabilities Index136.79122.91
ForecastBench61.557.1
ARC-AGI-20.4%—
SimpleBench27%—
ARC-AGI-15.5%—
Chess Puzzles6%—
EnigmaEval2.2%—
LMCA25.6%—
WinoGrande—83.5%

Math GPT-4.1 leads

GPT-4.1: 21.4 (#269), Llama 3-70B: 12.0 (#299)

BenchmarkGPT-4.1Llama 3-70B
OTIS Mock AIME 2024-202538.3%4.3%
LMArena Math13691218
MATH Level 583%22.6%
FrontierMath (Tiers 1-3)6%—
Omni-MATH47.1%—
FrontierMath (Feb 2025 set)5.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge GPT-4.1 leads

GPT-4.1: 37.0 (#152), Llama 3-70B: 20.8 (#272)

BenchmarkGPT-4.1Llama 3-70B
GPQA Diamond66.9%40.6%
LMArena Expert13641149
Humanity's Last Exam5.4%—
SimpleQA Verified31.1%—
MMLU-Pro81.1%—
Vectara Hallucination Rate5.6%—
GPQA (HELM)65.9%—
MMLU—79.3%

Multimodal Not comparable

GPT-4.1: 37.5 (#66), Llama 3-70B: —

BenchmarkGPT-4.1Llama 3-70B
LMArena Vision1210—
GeoBench72%—

Multilingual GPT-4.1 leads

GPT-4.1: 49.6 (#128), Llama 3-70B: 33.8 (#246)

BenchmarkGPT-4.1Llama 3-70B
LMArena Non-English13701142
LMArena Chinese13821114
LMArena French13831231
LMArena German13801169
LMArena Japanese13201017
LMArena Korean13391017
LMArena Russian13771159
LMArena Spanish13751241

Instruction Following GPT-4.1 leads

GPT-4.1: 71.5 (#148), Llama 3-70B: 62.8 (#233)

BenchmarkGPT-4.1Llama 3-70B
LMArena Instruction Following13671194
IFEval83.8%—

Long Context GPT-4.1 leads

GPT-4.1: 40.0 (#158), Llama 3-70B: 35.6 (#235)

BenchmarkGPT-4.1Llama 3-70B
LMArena Longer Query13851174
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.1 leads

GPT-4.1: 57.8 (#120), Llama 3-70B: 43.0 (#225)

BenchmarkGPT-4.1Llama 3-70B
LMArena Text13831221
LMArena Creative Writing13631210
LMArena Multi-Turn13981223
EQ-Bench Creative Writing1420—
WildBench85.4%—

Frequently asked questions

Is GPT-4.1 better than Llama 3-70B?

GPT-4.1 is the stronger model overall, scoring 35.7 to 28.5 on the Noometry Index.

Is GPT-4.1 or Llama 3-70B better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.3 versus 34.2 in the Noometry coding category.

How many benchmarks do GPT-4.1 and Llama 3-70B share?

24 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper