Noometry

Model comparison

GPT-4.1 vs Kimi K2.7 Code

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 35.7 on the Noometry Index.

Last verified . 9 shared benchmarks.

GPT-4.1 OpenAI

35.7

Rank #215 Confirmed

Kimi K2.7 Code Moonshot AI

43.0

Rank #90 Confirmed

Summary

  • They share 9 benchmarks with published results for both. GPT-4.1 scores higher in 1 category and Kimi K2.7 Code in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 21.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 95.6% for Kimi K2.7 Code.
  • Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $2 / $8 for GPT-4.1.
  • GPT-4.1 accepts more context: 1.05M tokens versus 262K.
  • Kimi K2.7 Code has downloadable open weights; the other is API-only.

Side by side

GPT-4.1Kimi K2.7 Code
ProviderOpenAIMoonshot AI
Noometry Index35.743.0
Released2025-04-142026-06-12
WeightsProprietaryOpen
Context window1.05M262K
Max output33K262K
Input $ / M tokens$2$0.95
Output $ / M tokens$8$4
Results tracked5219

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

Category by category

Coding Kimi K2.7 Code leads

GPT-4.1: 34.2 (#228), Kimi K2.7 Code: 42.4 (#92)

BenchmarkGPT-4.1Kimi K2.7 Code
WeirdML39%54.1%
ALE-Bench558.1886.23
SWE-bench Verified48.5%—
DeepSWE—30.5%
FrontierCode—30.1%
SWE-bench Verified (bash only)39.6%—
Aider Polyglot52.4%—
LMArena WebDev—1473
SciCode—47.5%
LMArena Coding1391—
CadEval42%—

Agentic & Tool Use GPT-4.1 leads

GPT-4.1: 34.4 (#40), Kimi K2.7 Code: 23.9 (#115)

BenchmarkGPT-4.1Kimi K2.7 Code
APEX-Agents—37.6%
Berkeley Function Calling Leaderboard54%—
GBAEval—0.9%
Vending-Bench 2—5,083

Reasoning Kimi K2.7 Code leads

GPT-4.1: 11.7 (#334), Kimi K2.7 Code: 38.2 (#56)

BenchmarkGPT-4.1Kimi K2.7 Code
SimpleBench27%57.9%
Chess Puzzles6%21%
Epoch Capabilities Index136.79150.01
ARC-AGI-20.4%—
Kagi LLM Benchmark52.3%—
ARC-AGI-15.5%—
CritPt—10%
EnigmaEval2.2%—
LMArena Hard Prompts1384—
DTBench68.3%—
LMCA25.6%—
Surface Evolver Bench—48.8%
ForecastBench61.5—

Math Kimi K2.7 Code leads

GPT-4.1: 21.4 (#269), Kimi K2.7 Code: 52.6 (#39)

BenchmarkGPT-4.1Kimi K2.7 Code
FrontierMath (Tiers 1-3)6%54%
OTIS Mock AIME 2024-202538.3%95.6%
FrontierMath Tier 4—12.2%
Omni-MATH47.1%—
LMArena Math1369—
MATH Level 583%—
FrontierMath (Feb 2025 set)5.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge Kimi K2.7 Code leads

GPT-4.1: 37.0 (#152), Kimi K2.7 Code: 53.6 (#51)

BenchmarkGPT-4.1Kimi K2.7 Code
GPQA Diamond66.9%87.9%
SimpleQA Verified31.1%36.5%
Humanity's Last Exam5.4%—
MMLU-Pro81.1%—
Vectara Hallucination Rate5.6%—
GPQA (HELM)65.9%—
LMArena Expert1364—

Multimodal Not comparable

GPT-4.1: 37.5 (#66), Kimi K2.7 Code: —

BenchmarkGPT-4.1Kimi K2.7 Code
LMArena Vision1210—
GeoBench72%—

Multilingual Not comparable

GPT-4.1: 49.6 (#128), Kimi K2.7 Code: —

BenchmarkGPT-4.1Kimi K2.7 Code
LMArena Non-English1370—
LMArena Chinese1382—
LMArena French1383—
LMArena German1380—
LMArena Japanese1320—
LMArena Korean1339—
LMArena Russian1377—
LMArena Spanish1375—

Instruction Following Not comparable

GPT-4.1: 71.5 (#148), Kimi K2.7 Code: —

BenchmarkGPT-4.1Kimi K2.7 Code
IFEval83.8%—
LMArena Instruction Following1367—

Long Context Not comparable

GPT-4.1: 40.0 (#158), Kimi K2.7 Code: —

BenchmarkGPT-4.1Kimi K2.7 Code
Fiction.LiveBench63.9%—
LMArena Longer Query1385—

Writing & Preference Not comparable

GPT-4.1: 57.8 (#120), Kimi K2.7 Code: —

BenchmarkGPT-4.1Kimi K2.7 Code
LMArena Text1383—
LMArena Creative Writing1363—
EQ-Bench Creative Writing1420—
WildBench85.4%—
LMArena Multi-Turn1398—

Frequently asked questions

Is GPT-4.1 better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 35.7 on the Noometry Index.

Which is cheaper, GPT-4.1 or Kimi K2.7 Code?

Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; GPT-4.1 lists at $2 and $8.

Is GPT-4.1 or Kimi K2.7 Code better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 34.2 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 does, with 1.05M tokens against 262K.

How many benchmarks do GPT-4.1 and Kimi K2.7 Code share?

9 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper