Noometry

Model comparison

GPT-5.4 mini vs o1-mini

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 33.7 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-5.4 mini OpenAI

44.8

Rank #69 Confirmed

o1-mini OpenAI

33.7

Rank #230 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 mini leads 30.3 to 8.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 63.7% for GPT-5.4 mini and 14% for o1-mini.

Side by side

GPT-5.4 minio1-mini
ProviderOpenAIOpenAI
Noometry Index44.833.7
Released2026-03-172024-09-12
WeightsProprietaryProprietary
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4639

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: 45.0 (#67), o1-mini: 35.1 (#218)

BenchmarkGPT-5.4 minio1-mini
WeirdML60.3%36.3%
LMArena Coding14381362
FrontierCode27%—
Aider Polyglot—32.9%
LMArena WebDev1397—
SciCode49.9%—
LiveBench Coding—48%
ALE-Bench1,189—
HumanEval+—89%
MBPP+—78.8%

Agentic & Tool Use GPT-5.4 mini leads

GPT-5.4 mini: 29.6 (#74), o1-mini: 24.3 (#112)

BenchmarkGPT-5.4 minio1-mini
Cybench—10%
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.3 (#77), o1-mini: 8.9 (#340)

BenchmarkGPT-5.4 minio1-mini
ARC-AGI-218.9%0.8%
ARC-AGI-163.7%14%
LMArena Hard Prompts14241333
Epoch Capabilities Index148.83135.82
SimpleBench—18.1%
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
CritPt10%—
Chess Puzzles24%—
Thematic Generalization61.7%—
LiveBench Reasoning—72.3%
Mystery Game Puzzles11%—
DTBench80%—
LiveBench Data Analysis—57.9%
LMCA40.8%—
ForecastBench57—
LiveBench—57.8%

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.4 (#63), o1-mini: 33.7 (#168)

BenchmarkGPT-5.4 minio1-mini
OTIS Mock AIME 2024-202588.9%46.9%
LMArena Math14181358
FrontierMath (Feb 2025 set)28.3%1.7%
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
ProofBench21%—
LiveBench Math—62%
MATH Level 5—89.2%
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.4 (#62), o1-mini: 34.8 (#180)

BenchmarkGPT-5.4 minio1-mini
GPQA Diamond86.9%62.4%
LMArena Expert14341316
SimpleQA Verified29.4%—
Confabulations—18.6%
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.0 (#51), o1-mini: —

BenchmarkGPT-5.4 minio1-mini
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 52.1 (#94), o1-mini: 43.8 (#177)

BenchmarkGPT-5.4 minio1-mini
LMArena Non-English14051289
LMArena Chinese14461314
LMArena French14401292
LMArena German14071278
LMArena Japanese13751245
LMArena Korean13691223
LMArena Russian14171283
LMArena Spanish14031302

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.3 (#99), o1-mini: 67.0 (#200)

BenchmarkGPT-5.4 minio1-mini
LMArena Instruction Following14051304
LiveBench Instruction Following—65.4%

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 42.9 (#107), o1-mini: 40.1 (#156)

BenchmarkGPT-5.4 minio1-mini
LMArena Longer Query14071321

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.2 (#56), o1-mini: 48.6 (#196)

BenchmarkGPT-5.4 minio1-mini
LMArena Text14111317
LMArena Creative Writing13701244
LMArena Multi-Turn14291314
Short-Story Creative Writing—64.9%
EQ-Bench Creative Writing1665—
LiveBench Language—40.9%

Frequently asked questions

Is GPT-5.4 mini better than o1-mini?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 33.7 on the Noometry Index.

Is GPT-5.4 mini or o1-mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 35.1 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and o1-mini share?

24 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and o1-mini has 39.

Related comparisons

Go deeper