Noometry

Model comparison

GPT-5.4 Pro vs Llama 3.1-405B

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 30.7 on the Noometry Index.

Last verified . 4 shared benchmarks.

GPT-5.4 Pro OpenAI

58.9

Rank #18 Confirmed

Llama 3.1-405B Meta

30.7

Rank #288 Confirmed

Summary

  • They share 4 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and Llama 3.1-405B in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.4 Pro leads 72.4 to 18.4.
  • The biggest single-benchmark swing is SimpleBench: 74.1% for GPT-5.4 Pro and 23% for Llama 3.1-405B.
  • Llama 3.1-405B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 ProLlama 3.1-405B
ProviderOpenAIMeta
Noometry Index58.930.7
Released2026-03-052024-07-23
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$30—
Output $ / M tokens$180—
Results tracked1642

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

Category by category

Coding GPT-5.4 Pro leads

GPT-5.4 Pro: 43.2 (#90), Llama 3.1-405B: 33.1 (#262)

BenchmarkGPT-5.4 ProLlama 3.1-405B
WeirdML57.4%21.4%
LMArena Coding—1291

Agentic & Tool Use Not comparable

GPT-5.4 Pro: —, Llama 3.1-405B: 21.0 (#140)

BenchmarkGPT-5.4 ProLlama 3.1-405B
TheAgentCompany—7.4%
Cybench—7.5%

Reasoning GPT-5.4 Pro leads

GPT-5.4 Pro: 70.7 (#13), Llama 3.1-405B: 16.8 (#300)

BenchmarkGPT-5.4 ProLlama 3.1-405B
SimpleBench74.1%23%
Epoch Capabilities Index158.93128.75
ARC-AGI-283.3%—
Kagi LLM Benchmark—45%
ARC-AGI-194.5%—
CritPt30%—
Chess Puzzles58.6%—
EnigmaEval23.8%—
LMArena Hard Prompts—1269
DTBench—61.4%
BIG-Bench Hard—82.9%
ForecastBench—59.9
HellaSwag—89.2%
PIQA—85.9%
WinoGrande—89.2%

Math GPT-5.4 Pro leads

GPT-5.4 Pro: 72.4 (#22), Llama 3.1-405B: 18.4 (#290)

BenchmarkGPT-5.4 ProLlama 3.1-405B
FrontierMath (Tiers 1-3)82.5%—
FrontierMath Tier 458.5%—
OTIS Mock AIME 2024-2025—9.7%
Omni-MATH—24.9%
LMArena Math—1281
MATH Level 5—49.8%
FrontierMath (Feb 2025 set)50%—
FrontierMath Tier 4 (v1)37.5%—

Knowledge GPT-5.4 Pro leads

GPT-5.4 Pro: 68.3 (#7), Llama 3.1-405B: 30.4 (#227)

BenchmarkGPT-5.4 ProLlama 3.1-405B
GPQA Diamond94.6%50.9%
Humanity's Last Exam44.3%—
SimpleQA Verified46.3%—
MMLU-Pro—72.3%
Confabulations—17.6%
Vectara Hallucination Rate8.3%—
GPQA (HELM)—52.2%
LMArena Expert—1243
ARC (AI2) Challenge—95.3%
MMLU—84.5%
TriviaQA—82.7%

Multilingual Not comparable

GPT-5.4 Pro: —, Llama 3.1-405B: 40.7 (#214)

BenchmarkGPT-5.4 ProLlama 3.1-405B
LMArena Non-English—1248
LMArena Chinese—1242
LMArena French—1279
LMArena German—1252
LMArena Japanese—1208
LMArena Korean—1184
LMArena Russian—1265
LMArena Spanish—1260

Instruction Following Not comparable

GPT-5.4 Pro: —, Llama 3.1-405B: 65.9 (#214)

BenchmarkGPT-5.4 ProLlama 3.1-405B
IFEval—81.1%
LMArena Instruction Following—1259

Long Context Not comparable

GPT-5.4 Pro: —, Llama 3.1-405B: 38.4 (#197)

BenchmarkGPT-5.4 ProLlama 3.1-405B
LMArena Longer Query—1266

Writing & Preference Not comparable

GPT-5.4 Pro: —, Llama 3.1-405B: 38.9 (#251)

BenchmarkGPT-5.4 ProLlama 3.1-405B
LMArena Text—1284
LMArena Creative Writing—1262
EQ-Bench Creative Writing—870
WildBench—78.3%
LMArena Multi-Turn—1297

Frequently asked questions

Is GPT-5.4 Pro better than Llama 3.1-405B?

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 30.7 on the Noometry Index.

Is GPT-5.4 Pro or Llama 3.1-405B better for coding?

GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 33.1 in the Noometry coding category.

How many benchmarks do GPT-5.4 Pro and Llama 3.1-405B share?

4 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Llama 3.1-405B has 42.

Related comparisons

Go deeper