Noometry

Model comparison

GPT-4.1 mini vs Kimi K2.5 Instant

Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 33.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4.1 mini OpenAI

33.5

Rank #232 Confirmed

Kimi K2.5 Instant Moonshot AI

42.9

Rank #92 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and Kimi K2.5 Instant in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Kimi K2.5 Instant leads 28.5 to 10.9.
  • Kimi K2.5 Instant has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniKimi K2.5 Instant
ProviderOpenAIMoonshot AI
Noometry Index33.542.9
Released2025-04-14—
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4718

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

Category by category

Coding Kimi K2.5 Instant leads

GPT-4.1 mini: 30.4 (#286), Kimi K2.5 Instant: 42.3 (#95)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Coding13671483
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
LMArena WebDev—1404
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.0 (#52), Kimi K2.5 Instant: —

BenchmarkGPT-4.1 miniKimi K2.5 Instant
Berkeley Function Calling Leaderboard50.5%—

Reasoning Kimi K2.5 Instant leads

GPT-4.1 mini: 10.9 (#335), Kimi K2.5 Instant: 28.5 (#88)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Hard Prompts13491443
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Epoch Capabilities Index135.01—

Math Kimi K2.5 Instant leads

GPT-4.1 mini: 23.1 (#264), Kimi K2.5 Instant: 36.6 (#105)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Math13431443
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge Kimi K2.5 Instant leads

GPT-4.1 mini: 34.7 (#183), Kimi K2.5 Instant: 39.5 (#121)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Expert13381438
GPQA Diamond65.8%—
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Kimi K2.5 Instant leads

GPT-4.1 mini: 35.2 (#77), Kimi K2.5 Instant: 39.5 (#47)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Vision11811254

Multilingual Kimi K2.5 Instant leads

GPT-4.1 mini: 45.9 (#161), Kimi K2.5 Instant: 52.2 (#89)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Non-English13181406
LMArena Chinese13291450
LMArena French13571403
LMArena German13491413
LMArena Korean12981378
LMArena Russian13241404
LMArena Spanish13191448
LMArena Japanese1291—

Instruction Following Kimi K2.5 Instant leads

GPT-4.1 mini: 73.9 (#113), Kimi K2.5 Instant: 75.5 (#61)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Instruction Following13321430
IFEval90.4%—

Long Context Kimi K2.5 Instant leads

GPT-4.1 mini: 31.8 (#270), Kimi K2.5 Instant: 43.8 (#82)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Longer Query13441435
Fiction.LiveBench44.4%—

Writing & Preference Kimi K2.5 Instant leads

GPT-4.1 mini: 48.8 (#193), Kimi K2.5 Instant: 60.8 (#91)

BenchmarkGPT-4.1 miniKimi K2.5 Instant
LMArena Text13411420
LMArena Creative Writing13001379
LMArena Multi-Turn13541427
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than Kimi K2.5 Instant?

Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 33.5 on the Noometry Index.

Is GPT-4.1 mini or Kimi K2.5 Instant better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.3 versus 30.4 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and Kimi K2.5 Instant share?

17 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Kimi K2.5 Instant has 18.

Related comparisons

Go deeper