Noometry

Model comparison

GPT-4.1 vs Llama 3.1-405B

GPT-4.1 is the stronger model overall, scoring 35.9 to 30.7 on the Noometry Index.

Last verified . 32 shared benchmarks.

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Llama 3.1-405B Meta

30.7

Rank #288 Confirmed

Summary

  • They share 32 benchmarks with published results for both. GPT-4.1 scores higher in 8 categories and Llama 3.1-405B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-4.1 leads 57.6 to 38.9.
  • The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 49.8% for Llama 3.1-405B.
  • Llama 3.1-405B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1Llama 3.1-405B
ProviderOpenAIMeta
Noometry Index35.930.7
Released2025-04-142024-07-23
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$2—
Output $ / M tokens$8—
Results tracked5242

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

Category by category

Coding GPT-4.1 leads

GPT-4.1: 34.4 (#238), Llama 3.1-405B: 33.1 (#262)

BenchmarkGPT-4.1Llama 3.1-405B
WeirdML39%21.4%
LMArena Coding13911291
SWE-bench Verified48.5%—
SWE-bench Verified (bash only)39.6%—
Aider Polyglot52.4%—
CadEval42%—
ALE-Bench558.1—

Agentic & Tool Use GPT-4.1 leads

GPT-4.1: 34.7 (#43), Llama 3.1-405B: 21.0 (#140)

BenchmarkGPT-4.1Llama 3.1-405B
Berkeley Function Calling Leaderboard54%—
TheAgentCompany—7.4%
Cybench—7.5%

Reasoning Llama 3.1-405B leads

GPT-4.1: 11.7 (#339), Llama 3.1-405B: 16.8 (#300)

BenchmarkGPT-4.1Llama 3.1-405B
SimpleBench27%23%
Kagi LLM Benchmark52.3%45%
LMArena Hard Prompts13841269
DTBench68.3%61.4%
Epoch Capabilities Index136.78128.75
ForecastBench61.559.9
ARC-AGI-20.4%—
ARC-AGI-15.5%—
Chess Puzzles6%—
EnigmaEval2.2%—
LMCA25.6%—
BIG-Bench Hard—82.9%
HellaSwag—89.2%
PIQA—85.9%
WinoGrande—89.2%

Math GPT-4.1 leads

GPT-4.1: 22.3 (#280), Llama 3.1-405B: 18.4 (#290)

BenchmarkGPT-4.1Llama 3.1-405B
OTIS Mock AIME 2024-202538.3%9.7%
Omni-MATH47.1%24.9%
LMArena Math13701281
MATH Level 583%49.8%
FrontierMath (Tiers 1-3)6%—
FrontierMath (Feb 2025 set)5.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge GPT-4.1 leads

GPT-4.1: 37.1 (#160), Llama 3.1-405B: 30.4 (#227)

BenchmarkGPT-4.1Llama 3.1-405B
GPQA Diamond66.9%50.9%
MMLU-Pro81.1%72.3%
GPQA (HELM)65.9%52.2%
LMArena Expert13641243
Humanity's Last Exam5.4%—
SimpleQA Verified31.1%—
Confabulations—17.6%
Vectara Hallucination Rate5.6%—
ARC (AI2) Challenge—95.3%
MMLU—84.5%
TriviaQA—82.7%

Multimodal Not comparable

GPT-4.1: 38.2 (#67), Llama 3.1-405B: —

BenchmarkGPT-4.1Llama 3.1-405B
LMArena Vision1211—
GeoBench72%—

Multilingual GPT-4.1 leads

GPT-4.1: 49.4 (#133), Llama 3.1-405B: 40.7 (#214)

BenchmarkGPT-4.1Llama 3.1-405B
LMArena Non-English13701248
LMArena Chinese13821242
LMArena French13821279
LMArena German13811252
LMArena Japanese13191208
LMArena Korean13391184
LMArena Russian13771265
LMArena Spanish13761260

Instruction Following GPT-4.1 leads

GPT-4.1: 71.3 (#153), Llama 3.1-405B: 65.9 (#214)

BenchmarkGPT-4.1Llama 3.1-405B
IFEval83.8%81.1%
LMArena Instruction Following13671259

Long Context GPT-4.1 leads

GPT-4.1: 40.0 (#163), Llama 3.1-405B: 38.4 (#197)

BenchmarkGPT-4.1Llama 3.1-405B
LMArena Longer Query13851266
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.1 leads

GPT-4.1: 57.6 (#125), Llama 3.1-405B: 38.9 (#251)

BenchmarkGPT-4.1Llama 3.1-405B
LMArena Text13831284
LMArena Creative Writing13631262
EQ-Bench Creative Writing1420870
WildBench85.4%78.3%
LMArena Multi-Turn13981297

Frequently asked questions

Is GPT-4.1 better than Llama 3.1-405B?

GPT-4.1 is the stronger model overall, scoring 35.9 to 30.7 on the Noometry Index.

Is GPT-4.1 or Llama 3.1-405B better for coding?

GPT-4.1 scores higher on coding benchmarks: 34.4 versus 33.1 in the Noometry coding category.

How many benchmarks do GPT-4.1 and Llama 3.1-405B share?

32 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Llama 3.1-405B has 42.

Related comparisons

Go deeper