Noometry

Model comparison

GPT-4.1 mini vs GPT-5.5 Instant

GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 33.6 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

GPT-5.5 Instant OpenAI

42.7

Rank #110 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and GPT-5.5 Instant in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.5 Instant leads 48.9 to 34.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 68.1% for GPT-5.5 Instant.

Side by side

GPT-4.1 miniGPT-5.5 Instant
ProviderOpenAIOpenAI
Noometry Index33.642.7
Released2025-04-142026-05-05
WeightsProprietaryProprietary
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4727

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

Category by category

Coding GPT-5.5 Instant leads

GPT-4.1 mini: 30.6 (#293), GPT-5.5 Instant: 44.3 (#74)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
SciCode40.4%48.6%
LMArena Coding13671433
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), GPT-5.5 Instant: —

BenchmarkGPT-4.1 miniGPT-5.5 Instant
Berkeley Function Calling Leaderboard50.5%—

Reasoning GPT-5.5 Instant leads

GPT-4.1 mini: 10.8 (#340), GPT-5.5 Instant: 24.9 (#155)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
CritPt0%0%
Chess Puzzles7%12%
LMArena Hard Prompts13491426
Epoch Capabilities Index135.01142.52
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—

Math GPT-5.5 Instant leads

GPT-4.1 mini: 24.1 (#270), GPT-5.5 Instant: 26.5 (#259)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
FrontierMath (Tiers 1-3)6.7%26.3%
OTIS Mock AIME 2024-202544.7%68.1%
LMArena Math13431420
FrontierMath Tier 4—2.4%
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge GPT-5.5 Instant leads

GPT-4.1 mini: 34.7 (#194), GPT-5.5 Instant: 48.9 (#74)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
GPQA Diamond65.8%82.5%
LMArena Expert13381409
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal GPT-5.5 Instant leads

GPT-4.1 mini: 35.8 (#82), GPT-5.5 Instant: 40.0 (#52)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
LMArena Vision11811250
LMArena Document—1403

Multilingual GPT-5.5 Instant leads

GPT-4.1 mini: 45.7 (#166), GPT-5.5 Instant: 52.8 (#80)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
LMArena Non-English13181417
LMArena Chinese13291456
LMArena French13581428
LMArena German13511411
LMArena Japanese12901408
LMArena Korean12981392
LMArena Russian13241431
LMArena Spanish13191429

Instruction Following Too close to call

GPT-4.1 mini: 73.7 (#118), GPT-5.5 Instant: 74.2 (#100)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
LMArena Instruction Following13331406
IFEval90.4%—

Long Context GPT-5.5 Instant leads

GPT-4.1 mini: 31.8 (#275), GPT-5.5 Instant: 43.4 (#96)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
LMArena Longer Query13441422
Fiction.LiveBench44.4%—

Writing & Preference GPT-5.5 Instant leads

GPT-4.1 mini: 48.6 (#199), GPT-5.5 Instant: 61.8 (#85)

BenchmarkGPT-4.1 miniGPT-5.5 Instant
LMArena Text13401419
LMArena Creative Writing13001419
LMArena Multi-Turn13541433
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than GPT-5.5 Instant?

GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 33.6 on the Noometry Index.

Is GPT-4.1 mini or GPT-5.5 Instant better for coding?

GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 30.6 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and GPT-5.5 Instant share?

25 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5.5 Instant has 27.

Related comparisons

Go deeper