Noometry

Model comparison

GPT-4.1 mini vs o1-mini

GPT-4.1 mini and o1-mini score almost the same on the Noometry Index (33.6 vs 34.0), so choose on price, context window or the category you care about most.

Last verified . 26 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

o1-mini OpenAI

34.0

Rank #235 Confirmed

Summary

  • They share 26 benchmarks with published results for both. GPT-4.1 mini scores higher in 5 categories and o1-mini in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where o1-mini leads 35.4 to 24.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 14% for o1-mini.

Side by side

GPT-4.1 minio1-mini
ProviderOpenAIOpenAI
Noometry Index33.634.0
Released2025-04-142024-09-12
WeightsProprietaryProprietary
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4739

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

Category by category

Coding o1-mini leads

GPT-4.1 mini: 30.6 (#293), o1-mini: 35.5 (#224)

BenchmarkGPT-4.1 minio1-mini
Aider Polyglot32.4%32.9%
WeirdML37.6%36.3%
LMArena Coding13671362
SWE-bench Verified (bash only)23.9%—
SciCode40.4%—
BigCodeBench Instruct48.9%—
LiveBench Coding—48%
CadEval16%—
HumanEval+—89%
MBPP+—78.8%

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.3 (#55), o1-mini: 24.6 (#118)

BenchmarkGPT-4.1 minio1-mini
Berkeley Function Calling Leaderboard50.5%—
Cybench—10%

Reasoning GPT-4.1 mini leads

GPT-4.1 mini: 10.8 (#340), o1-mini: 8.8 (#346)

BenchmarkGPT-4.1 minio1-mini
ARC-AGI-20%0.8%
ARC-AGI-13.5%14%
LMArena Hard Prompts13491333
Epoch Capabilities Index135.01135.82
SimpleBench—18.1%
Kagi LLM Benchmark48.6%—
CritPt0%—
Chess Puzzles7%—
LiveBench Reasoning—72.3%
Mystery Game Puzzles7%—
DTBench68.8%—
LiveBench Data Analysis—57.9%
LMCA21.1%—
LiveBench—57.8%

Math o1-mini leads

GPT-4.1 mini: 24.1 (#270), o1-mini: 35.4 (#186)

BenchmarkGPT-4.1 minio1-mini
OTIS Mock AIME 2024-202544.7%46.9%
LMArena Math13431358
MATH Level 587.3%89.2%
FrontierMath (Feb 2025 set)4.5%1.7%
FrontierMath (Tiers 1-3)6.7%—
Omni-MATH49.1%—
LiveBench Math—62%

Knowledge Too close to call

GPT-4.1 mini: 34.7 (#194), o1-mini: 34.9 (#192)

BenchmarkGPT-4.1 minio1-mini
GPQA Diamond65.8%62.4%
LMArena Expert13381316
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
Confabulations—18.6%
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), o1-mini: —

BenchmarkGPT-4.1 minio1-mini
LMArena Vision1181—

Multilingual GPT-4.1 mini leads

GPT-4.1 mini: 45.7 (#166), o1-mini: 43.6 (#182)

BenchmarkGPT-4.1 minio1-mini
LMArena Non-English13181289
LMArena Chinese13291314
LMArena French13581293
LMArena German13511278
LMArena Japanese12901245
LMArena Korean12981223
LMArena Russian13241283
LMArena Spanish13191303

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), o1-mini: 66.7 (#206)

BenchmarkGPT-4.1 minio1-mini
LMArena Instruction Following13331304
LiveBench Instruction Following—65.4%
IFEval90.4%—

Long Context o1-mini leads

GPT-4.1 mini: 31.8 (#275), o1-mini: 40.1 (#161)

BenchmarkGPT-4.1 minio1-mini
LMArena Longer Query13441320
Fiction.LiveBench44.4%—

Writing & Preference Too close to call

GPT-4.1 mini: 48.6 (#199), o1-mini: 48.4 (#202)

BenchmarkGPT-4.1 minio1-mini
LMArena Text13401317
LMArena Creative Writing13001244
LMArena Multi-Turn13541314
Short-Story Creative Writing—64.9%
EQ-Bench Creative Writing1147—
WildBench83.8%—
LiveBench Language—40.9%

Frequently asked questions

Is GPT-4.1 mini better than o1-mini?

GPT-4.1 mini and o1-mini score almost the same on the Noometry Index (33.6 vs 34.0), so choose on price, context window or the category you care about most.

Is GPT-4.1 mini or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.5 versus 30.6 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and o1-mini share?

26 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and o1-mini has 39.

Related comparisons

Go deeper