Noometry

Model comparison

GPT-4o mini vs GPT-5.2

GPT-5.2 is the stronger model overall, scoring 54.1 to 25.5 on the Noometry Index. GPT-4o mini costs 18× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.

Last verified . 33 shared benchmarks.

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Summary

  • They share 33 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and GPT-5.2 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.2 leads 60.0 to 10.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 96.1% for GPT-5.2.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
  • GPT-5.2 accepts more context: 400K tokens versus 128K.

Side by side

GPT-4o miniGPT-5.2
ProviderOpenAIOpenAI
Noometry Index25.554.1
Released2024-07-182025-12-11
WeightsProprietaryProprietary
Context window128K400K
Max output16K128K
Input $ / M tokens$0.15$1.75
Output $ / M tokens$0.60$14
Results tracked6067

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

Category by category

Coding GPT-5.2 leads

GPT-4o mini: 22.0 (#335), GPT-5.2: 51.6 (#37)

BenchmarkGPT-4o miniGPT-5.2
WeirdML11.8%72.2%
LMArena Coding12901447
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—72.8%
Aider Polyglot3.6%—
LMArena WebDev—1416
SWE-bench Multilingual—66.7%
GSO—27.4%
BigCodeBench Instruct46.1%—
LiveBench Coding43.1%—
BigCodeBench Complete57.4%—
ALE-Bench—1,294
AlgoTune—2.05
HumanEval+83.5%—
MBPP+72.2%—

Agentic & Tool Use GPT-5.2 leads

GPT-4o mini: 27.5 (#101), GPT-5.2: 40.2 (#24)

BenchmarkGPT-4o miniGPT-5.2
Terminal-Bench—64.9%
Berkeley Function Calling Leaderboard—55.9%
GDPval—49.7%
Remote Labor Index—2.5%
τ²-bench Airline—83%
τ²-bench Banking—32.2%
τ²-bench Retail—81.6%
τ²-bench Telecom—89.7%
DeepResearch Bench—41.1%
BALROG17.4%—
LMArena Search—1207
METR Time Horizons—75.3%
Vending-Bench 2—3,591

Reasoning GPT-5.2 leads

GPT-4o mini: 8.7 (#347), GPT-5.2: 50.2 (#35)

BenchmarkGPT-4o miniGPT-5.2
ARC-AGI-20%52.9%
SimpleBench10.7%45.8%
Kagi LLM Benchmark28.8%73.3%
Chess Puzzles0%49%
LMArena Hard Prompts12671445
Mystery Game Puzzles12%23%
DTBench54.4%90.9%
LMCA10.4%43.9%
Epoch Capabilities Index126.56153.45
NYT Connections (extended)—83.6%
ARC-AGI-1—86.2%
EnigmaEval—10.4%
EBR-Bench—23%
LiveBench Reasoning32.8%—
LiveBench Data Analysis50%—
ForecastBench—60.1
LiveBench41.3%—
PIQA88.7%—

Math GPT-5.2 leads

GPT-4o mini: 10.4 (#314), GPT-5.2: 60.0 (#38)

BenchmarkGPT-4o miniGPT-5.2
FrontierMath (Tiers 1-3)0.7%67.4%
OTIS Mock AIME 2024-20256.9%96.1%
LMArena Math12671440
FrontierMath Tier 4—31.7%
MathArena Final-Answer Competitions—72%
ProofBench—15%
Omni-MATH28%—
LiveBench Math36.3%—
MATH Level 552.6%—
FrontierMath (Feb 2025 set)—40.7%
FrontierMath Tier 4 (v1)—18.8%
GSM8K91.3%—

Knowledge GPT-5.2 leads

GPT-4o mini: 17.7 (#284), GPT-5.2: 59.3 (#32)

BenchmarkGPT-4o miniGPT-5.2
GPQA Diamond37.7%91.4%
SimpleQA Verified8.3%37.1%
LMArena Expert12351445
Humanity's Last Exam—27.8%
MMLU-Pro60.3%—
Confabulations37.2%—
Vectara Hallucination Rate—8.4%
GPQA (HELM)36.8%—
BoolQ88.7%—
MMLU81.8%—

Multimodal GPT-5.2 leads

GPT-4o mini: 25.9 (#122), GPT-5.2: 51.3 (#7)

BenchmarkGPT-4o miniGPT-5.2
LMArena Vision10661268
VPCT34%84%
Video-MME64.8%—
GeoBench64%—
Furniture Assembly—38.3%
LMArena Document—1405

Multilingual GPT-5.2 leads

GPT-4o mini: 42.0 (#199), GPT-5.2: 53.4 (#67)

BenchmarkGPT-4o miniGPT-5.2
LMArena Non-English12661425
LMArena Chinese12651460
LMArena French12971455
LMArena German12721448
LMArena Japanese12161420
LMArena Korean11951392
LMArena Russian12751440
LMArena Spanish12761433

Instruction Following GPT-5.2 leads

GPT-4o mini: 61.9 (#239), GPT-5.2: 74.7 (#89)

BenchmarkGPT-4o miniGPT-5.2
LMArena Instruction Following12581417
LiveBench Instruction Following56.8%—
IFEval78.2%—

Long Context GPT-5.2 leads

GPT-4o mini: 39.1 (#186), GPT-5.2: 44.0 (#78)

BenchmarkGPT-4o miniGPT-5.2
LMArena Longer Query12891428
CL-bench—18.2%

Writing & Preference GPT-5.2 leads

GPT-4o mini: 39.5 (#248), GPT-5.2: 66.8 (#32)

BenchmarkGPT-4o miniGPT-5.2
LMArena Text12861439
LMArena Creative Writing12681401
EQ-Bench Creative Writing8731703
LMArena Multi-Turn12851458
Short-Story Creative Writing67.2%—
WildBench79.1%—
LiveBench Language28.6%—

Frequently asked questions

Is GPT-4o mini better than GPT-5.2?

GPT-5.2 is the stronger model overall, scoring 54.1 to 25.5 on the Noometry Index. GPT-4o mini costs 18× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.

Which is cheaper, GPT-4o mini or GPT-5.2?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-5.2 lists at $1.75 and $14.

Is GPT-4o mini or GPT-5.2 better for coding?

GPT-5.2 scores higher on coding benchmarks: 51.6 versus 22.0 in the Noometry coding category.

Which has the bigger context window?

GPT-5.2 does, with 400K tokens against 128K.

How many benchmarks do GPT-4o mini and GPT-5.2 share?

33 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and GPT-5.2 has 67.

Related comparisons

Go deeper