Noometry

Model comparison

GPT-5.4 mini vs Longcat Flash Chat

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 41.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-5.4 mini OpenAI

44.8

Rank #69 Confirmed

Longcat Flash Chat Meituan

41.5

Rank #121 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-5.4 mini scores higher in 6 categories and Longcat Flash Chat in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 mini leads 30.3 to 18.3.
  • The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 17.7% for Longcat Flash Chat.
  • Longcat Flash Chat has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniLongcat Flash Chat
ProviderOpenAIMeituan
Noometry Index44.841.5
Released2026-03-17—
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4619

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.0 (#67), Longcat Flash Chat: 42.9 (#85)

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Coding14381471
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.6 (#74), Longcat Flash Chat: —

BenchmarkGPT-5.4 miniLongcat Flash Chat
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.3 (#77), Longcat Flash Chat: 18.3 (#267)

BenchmarkGPT-5.4 miniLongcat Flash Chat
Kagi LLM Benchmark37.9%43.9%
NYT Connections (extended)61.8%17.7%
LMArena Hard Prompts14241440
ARC-AGI-218.9%—
ARC-AGI-163.7%—
CritPt10%—
Chess Puzzles24%—
Thematic Generalization61.7%—
Mystery Game Puzzles11%—
DTBench80%—
LMCA40.8%—
Epoch Capabilities Index148.83—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.4 (#63), Longcat Flash Chat: 36.6 (#107)

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Math14181441
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
ProofBench21%—
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.4 (#62), Longcat Flash Chat: 40.0 (#111)

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Expert14341454
GPQA Diamond86.9%—
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.0 (#51), Longcat Flash Chat: —

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Vision1245—

Multilingual Too close to call

GPT-5.4 mini: 52.1 (#94), Longcat Flash Chat: 52.1 (#95)

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Non-English14051404
LMArena Chinese14461465
LMArena French14401457
LMArena German14071409
LMArena Japanese13751373
LMArena Korean13691372
LMArena Russian14171396
LMArena Spanish14031445

Instruction Following Too close to call

GPT-5.4 mini: 74.3 (#99), Longcat Flash Chat: 74.6 (#92)

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Instruction Following14051411

Long Context Too close to call

GPT-5.4 mini: 42.9 (#107), Longcat Flash Chat: 43.5 (#89)

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Longer Query14071425

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.2 (#56), Longcat Flash Chat: 61.2 (#88)

BenchmarkGPT-5.4 miniLongcat Flash Chat
LMArena Text14111427
LMArena Creative Writing13701388
LMArena Multi-Turn14291418
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Longcat Flash Chat?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 41.5 on the Noometry Index.

Is GPT-5.4 mini or Longcat Flash Chat better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 42.9 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and Longcat Flash Chat share?

19 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Longcat Flash Chat has 19.

Related comparisons

Go deeper