Noometry

Model comparison

o1-mini vs o4-mini

o4-mini is the stronger model overall, scoring 41.6 to 33.7 on the Noometry Index.

Last verified . 29 shared benchmarks.

o1-mini OpenAI

33.7

Rank #230 Confirmed

o4-mini OpenAI

41.6

Rank #119 Confirmed

Summary

  • They share 29 benchmarks with published results for both. o1-mini scores higher in 0 categories and o4-mini in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where o4-mini leads 24.6 to 8.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 14% for o1-mini and 58.7% for o4-mini.

Side by side

o1-minio4-mini
ProviderOpenAIOpenAI
Noometry Index33.741.6
Released2024-09-122025-04-16
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$1.10
Output $ / M tokens—$4.40
Results tracked3960

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

Category by category

Coding o4-mini leads

o1-mini: 35.1 (#218), o4-mini: 41.6 (#110)

Benchmarko1-minio4-mini
Aider Polyglot32.9%72%
WeirdML36.3%52.6%
LMArena Coding13621369
SWE-bench Verified (bash only)—45%
GSO—3.6%
LiveBench Coding48%—
CadEval—62%
ALE-Bench—826.17
AlgoTune—1.72
HumanEval+89%—
MBPP+78.8%—

Agentic & Tool Use o4-mini leads

o1-mini: 24.3 (#112), o4-mini: 32.3 (#57)

Benchmarko1-minio4-mini
Berkeley Function Calling Leaderboard—53.2%
GDPval—25.3%
Cybench10%—
METR Time Horizons—63.9%

Reasoning o4-mini leads

o1-mini: 8.9 (#340), o4-mini: 24.6 (#143)

Benchmarko1-minio4-mini
ARC-AGI-20.8%6.1%
SimpleBench18.1%38.7%
ARC-AGI-114%58.7%
LMArena Hard Prompts13331351
Epoch Capabilities Index135.82145.63
Kagi LLM Benchmark—67.6%
CritPt—0.6%
Chess Puzzles—26%
EnigmaEval—9.2%
LiveBench Reasoning72.3%—
Mystery Game Puzzles—5%
DTBench—77.6%
LiveBench Data Analysis57.9%—
LMCA—26.5%
ForecastBench—61.8
LiveBench57.8%—

Math o4-mini leads

o1-mini: 33.7 (#168), o4-mini: 40.2 (#79)

Benchmarko1-minio4-mini
OTIS Mock AIME 2024-202546.9%81.7%
LMArena Math13581390
MATH Level 589.2%97.8%
FrontierMath (Feb 2025 set)1.7%24.8%
FrontierMath (Tiers 1-3)—36.1%
FrontierMath Tier 4—4.9%
Omni-MATH—72%
LiveBench Math62%—
FrontierMath Tier 4 (v1)—6.3%

Knowledge o4-mini leads

o1-mini: 34.8 (#180), o4-mini: 43.5 (#83)

Benchmarko1-minio4-mini
GPQA Diamond62.4%79.6%
Confabulations18.6%15.8%
LMArena Expert13161344
Humanity's Last Exam—18.1%
SimpleQA Verified—19.6%
MMLU-Pro—82%
Vectara Hallucination Rate—18.6%
GPQA (HELM)—73.5%

Multimodal Not comparable

o1-mini: —, o4-mini: 39.5 (#46)

Benchmarko1-minio4-mini
LMArena Vision—1194
GeoBench—64%
VPCT—57.5%

Multilingual o4-mini leads

o1-mini: 43.8 (#177), o4-mini: 47.2 (#149)

Benchmarko1-minio4-mini
LMArena Non-English12891336
LMArena Chinese13141355
LMArena French12921362
LMArena German12781336
LMArena Japanese12451308
LMArena Korean12231313
LMArena Russian12831334
LMArena Spanish13021346

Instruction Following o4-mini leads

o1-mini: 67.0 (#200), o4-mini: 75.4 (#63)

Benchmarko1-minio4-mini
LMArena Instruction Following13041321
LiveBench Instruction Following65.4%—
IFEval—92.8%

Long Context o4-mini leads

o1-mini: 40.1 (#156), o4-mini: 45.5 (#31)

Benchmarko1-minio4-mini
LMArena Longer Query13211315
Fiction.LiveBench—77.8%

Writing & Preference o4-mini leads

o1-mini: 48.6 (#196), o4-mini: 54.2 (#148)

Benchmarko1-minio4-mini
LMArena Text13171353
LMArena Creative Writing12441294
Short-Story Creative Writing64.9%75%
LMArena Multi-Turn13141350
WildBench—85.4%
LiveBench Language40.9%—

Frequently asked questions

Is o1-mini better than o4-mini?

o4-mini is the stronger model overall, scoring 41.6 to 33.7 on the Noometry Index.

Is o1-mini or o4-mini better for coding?

o4-mini scores higher on coding benchmarks: 41.6 versus 35.1 in the Noometry coding category.

How many benchmarks do o1-mini and o4-mini share?

29 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper