Noometry

Model comparison

GPT-4o mini vs GPT-5.5

GPT-5.5 is the stronger model overall, scoring 63.4 to 25.5 on the Noometry Index. GPT-4o mini costs 43× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

Last verified . 32 shared benchmarks.

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

GPT-5.5 OpenAI

63.4

Rank #9 Confirmed

Summary

  • They share 32 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and GPT-5.5 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.5 leads 81.7 to 10.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 100% for GPT-5.5.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $5 / $30 for GPT-5.5.
  • GPT-5.5 accepts more context: 1.05M tokens versus 128K.

Side by side

GPT-4o miniGPT-5.5
ProviderOpenAIOpenAI
Noometry Index25.563.4
Released2024-07-182026-04-23
WeightsProprietaryProprietary
Context window128K1.05M
Max output16K128K
Input $ / M tokens$0.15$5
Output $ / M tokens$0.60$30
Results tracked6071

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

Category by category

Coding GPT-5.5 leads

GPT-4o mini: 22.0 (#335), GPT-5.5: 58.2 (#17)

BenchmarkGPT-4o miniGPT-5.5
WeirdML11.8%84.9%
LMArena Coding12901494
SWE-bench Verified—80.6%
DeepSWE—67%
FrontierCode—43%
Aider Polyglot3.6%—
LMArena WebDev—1513
SciCode—56.1%
GSO—40.2%
BigCodeBench Instruct46.1%—
LiveBench Coding43.1%—
MirrorCode—10%
BigCodeBench Complete57.4%—
ALE-Bench—1,943
HumanEval+83.5%—
MBPP+72.2%—

Agentic & Tool Use GPT-5.5 leads

GPT-4o mini: 27.5 (#101), GPT-5.5: 50.7 (#6)

BenchmarkGPT-4o miniGPT-5.5
Terminal-Bench—84.7%
APEX-Agents—55.1%
OSWorld 2.0—13%
Remote Labor Index—6.3%
τ²-bench Banking—44.6%
DeepResearch Bench—54%
PostTrainBench—27.2%
BALROG17.4%—
ExploitBench—47.4%
GBAEval—53.2%
GDP.pdf—26%
LMArena Search—1242
Vending-Bench 2—7,524

Reasoning GPT-5.5 leads

GPT-4o mini: 8.7 (#347), GPT-5.5: 72.8 (#11)

BenchmarkGPT-4o miniGPT-5.5
ARC-AGI-20%85%
SimpleBench10.7%69%
Kagi LLM Benchmark28.8%88.8%
Chess Puzzles0%54%
LMArena Hard Prompts12671489
Mystery Game Puzzles12%56%
DTBench54.4%96%
LMCA10.4%54.3%
Epoch Capabilities Index126.56159.1
NYT Connections (extended)—96.2%
ARC-AGI-1—95%
CritPt—27.1%
EBR-Bench—34.3%
LiveBench Reasoning32.8%—
LiveBench Data Analysis50%—
Surface Evolver Bench—88.1%
Bench to the Future 3—0.14
ForecastBench—60.6
LiveBench41.3%—
PIQA88.7%—

Math GPT-5.5 leads

GPT-4o mini: 10.4 (#314), GPT-5.5: 81.7 (#11)

BenchmarkGPT-4o miniGPT-5.5
FrontierMath (Tiers 1-3)0.7%85.3%
OTIS Mock AIME 2024-20256.9%100%
LMArena Math12671486
FrontierMath Tier 4—72.5%
MathArena Final-Answer Competitions—94.3%
ProofBench—50%
Omni-MATH28%—
LiveBench Math36.3%—
MATH Level 552.6%—
FrontierMath (Feb 2025 set)—51.7%
FrontierMath Erdős—0%
FrontierMath Tier 4 (v1)—35.4%
GSM8K91.3%—

Knowledge GPT-5.5 leads

GPT-4o mini: 17.7 (#284), GPT-5.5: 64.4 (#17)

BenchmarkGPT-4o miniGPT-5.5
GPQA Diamond37.7%94%
SimpleQA Verified8.3%63%
LMArena Expert12351508
MMLU-Pro60.3%—
Confabulations37.2%—
Vectara Hallucination Rate—9.3%
GPQA (HELM)36.8%—
BoolQ88.7%—
MMLU81.8%—

Multimodal GPT-5.5 leads

GPT-4o mini: 25.9 (#122), GPT-5.5: 46.9 (#12)

BenchmarkGPT-4o miniGPT-5.5
LMArena Vision10661297
Video-MME64.8%—
GeoBench64%—
VPCT34%—
Blueprint-Bench 2—36.2%
Furniture Assembly—44.2%
LMArena Document—1486

Multilingual GPT-5.5 leads

GPT-4o mini: 42.0 (#199), GPT-5.5: 56.4 (#20)

BenchmarkGPT-4o miniGPT-5.5
LMArena Non-English12661467
LMArena Chinese12651533
LMArena French12971486
LMArena German12721480
LMArena Japanese12161498
LMArena Korean11951460
LMArena Russian12751473
LMArena Spanish12761468

Instruction Following GPT-5.5 leads

GPT-4o mini: 61.9 (#239), GPT-5.5: 77.5 (#18)

BenchmarkGPT-4o miniGPT-5.5
LMArena Instruction Following12581479
LiveBench Instruction Following56.8%—
IFEval78.2%—

Long Context GPT-5.5 leads

GPT-4o mini: 39.1 (#186), GPT-5.5: 48.3 (#12)

BenchmarkGPT-4o miniGPT-5.5
LMArena Longer Query12891484
CL-bench Life—22.2%

Writing & Preference GPT-5.5 leads

GPT-4o mini: 39.5 (#248), GPT-5.5: 72.7 (#13)

BenchmarkGPT-4o miniGPT-5.5
LMArena Text12861472
LMArena Creative Writing12681455
EQ-Bench Creative Writing8731844
LMArena Multi-Turn12851476
Short-Story Creative Writing67.2%—
WildBench79.1%—
EQ-Bench 4—1315
LiveBench Language28.6%—

Frequently asked questions

Is GPT-4o mini better than GPT-5.5?

GPT-5.5 is the stronger model overall, scoring 63.4 to 25.5 on the Noometry Index. GPT-4o mini costs 43× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

Which is cheaper, GPT-4o mini or GPT-5.5?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-5.5 lists at $5 and $30.

Is GPT-4o mini or GPT-5.5 better for coding?

GPT-5.5 scores higher on coding benchmarks: 58.2 versus 22.0 in the Noometry coding category.

Which has the bigger context window?

GPT-5.5 does, with 1.05M tokens against 128K.

How many benchmarks do GPT-4o mini and GPT-5.5 share?

32 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and GPT-5.5 has 71.

Related comparisons

Go deeper