Noometry

Model comparison

GPT-5.4 mini vs Kimi K2.5 Instant

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 42.9 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-5.4 mini OpenAI

44.8

Rank #69 Confirmed

Kimi K2.5 Instant Moonshot AI

42.9

Rank #92 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-5.4 mini scores higher in 5 categories and Kimi K2.5 Instant in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 39.5.
  • Kimi K2.5 Instant has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniKimi K2.5 Instant
ProviderOpenAIMoonshot AI
Noometry Index44.842.9
Released2026-03-17—
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4618

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), Kimi K2.5 Instant: 42.3 (#95)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena WebDev13971404
LMArena Coding14381483
FrontierCode27%—
SciCode49.9%—
WeirdML60.3%—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.6 (#74), Kimi K2.5 Instant: —

BenchmarkGPT-5.4 miniKimi K2.5 Instant
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.3 (#77), Kimi K2.5 Instant: 28.5 (#88)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Hard Prompts14241443
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
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), Kimi K2.5 Instant: 36.6 (#105)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Math14181443
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), Kimi K2.5 Instant: 39.5 (#121)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Expert14341438
GPQA Diamond86.9%—
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—

Multimodal Too close to call

GPT-5.4 mini: 39.0 (#51), Kimi K2.5 Instant: 39.5 (#47)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Vision12451254

Multilingual Too close to call

GPT-5.4 mini: 52.1 (#94), Kimi K2.5 Instant: 52.2 (#89)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Non-English14051406
LMArena Chinese14461450
LMArena French14401403
LMArena German14071413
LMArena Korean13691378
LMArena Russian14171404
LMArena Spanish14031448
LMArena Japanese1375—

Instruction Following Kimi K2.5 Instant leads

GPT-5.4 mini: 74.3 (#99), Kimi K2.5 Instant: 75.5 (#61)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Instruction Following14051430

Long Context Too close to call

GPT-5.4 mini: 42.9 (#107), Kimi K2.5 Instant: 43.8 (#82)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Longer Query14071435

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.2 (#56), Kimi K2.5 Instant: 60.8 (#91)

BenchmarkGPT-5.4 miniKimi K2.5 Instant
LMArena Text14111420
LMArena Creative Writing13701379
LMArena Multi-Turn14291427
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Kimi K2.5 Instant?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 42.9 on the Noometry Index.

Is GPT-5.4 mini or Kimi K2.5 Instant better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 42.3 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and Kimi K2.5 Instant share?

18 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Kimi K2.5 Instant has 18.

Related comparisons

Go deeper