Noometry

Model comparison

GPT-4.5 vs Kimi K2.7 Code

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 37.2 on the Noometry Index.

Last verified . 5 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Summary

  • They share 5 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and Kimi K2.7 Code in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Kimi K2.7 Code leads 39.0 to 13.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 95.6% for Kimi K2.7 Code.
  • Kimi K2.7 Code has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Kimi K2.7 Code
ProviderOpenAIMoonshot AI
Noometry Index37.243.3
Released2025-02-272026-06-12
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.95
Output $ / M tokens—$4
Results tracked4219

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

Category by category

Coding Too close to call

GPT-4.5: 42.2 (#109), Kimi K2.7 Code: 42.9 (#95)

BenchmarkGPT-4.5Kimi K2.7 Code
WeirdML39.4%54.1%
DeepSWE—30.5%
FrontierCode—30.1%
Aider Polyglot44.9%—
LMArena WebDev—1473
SciCode—47.5%
LiveBench Coding75.2%—
LMArena Coding1396—
ALE-Bench—886.23

Agentic & Tool Use GPT-4.5 leads

GPT-4.5: 27.9 (#97), Kimi K2.7 Code: 24.0 (#122)

BenchmarkGPT-4.5Kimi K2.7 Code
APEX-Agents—37.6%
Cybench17.5%—
GBAEval—0.9%
Vending-Bench 2—5,083

Reasoning Kimi K2.7 Code leads

GPT-4.5: 13.9 (#330), Kimi K2.7 Code: 39.0 (#61)

BenchmarkGPT-4.5Kimi K2.7 Code
SimpleBench34.5%57.9%
Epoch Capabilities Index136.74149.97
ARC-AGI-20.8%—
ARC-AGI-110.3%—
CritPt—10%
Chess Puzzles—21%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LMArena Hard Prompts1403—
LiveBench Data Analysis64.3%—
Surface Evolver Bench—48.8%
ForecastBench61.7—
LiveBench69%—

Math Kimi K2.7 Code leads

GPT-4.5: 32.6 (#211), Kimi K2.7 Code: 52.9 (#48)

BenchmarkGPT-4.5Kimi K2.7 Code
OTIS Mock AIME 2024-202537.8%95.6%
FrontierMath (Tiers 1-3)—54%
FrontierMath Tier 4—12.2%
LiveBench Math69.3%—
LMArena Math1412—
MATH Level 578.6%—

Knowledge Kimi K2.7 Code leads

GPT-4.5: 32.5 (#211), Kimi K2.7 Code: 53.5 (#57)

BenchmarkGPT-4.5Kimi K2.7 Code
GPQA Diamond68.7%87.9%
Humanity's Last Exam5.4%—
SimpleQA Verified—36.5%
Confabulations13.6%—
LMArena Expert1394—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Kimi K2.7 Code: —

BenchmarkGPT-4.5Kimi K2.7 Code
LMArena Vision1195—
VPCT45%—

Multilingual Not comparable

GPT-4.5: 52.5 (#83), Kimi K2.7 Code: —

BenchmarkGPT-4.5Kimi K2.7 Code
LMArena Non-English1413—
LMArena Chinese1421—
LMArena French1418—
LMArena German1457—
LMArena Japanese1416—
LMArena Korean1392—
LMArena Russian1419—

Instruction Following Not comparable

GPT-4.5: 72.6 (#134), Kimi K2.7 Code: —

BenchmarkGPT-4.5Kimi K2.7 Code
LiveBench Instruction Following72.3%—
LMArena Instruction Following1404—

Long Context Not comparable

GPT-4.5: 40.4 (#155), Kimi K2.7 Code: —

BenchmarkGPT-4.5Kimi K2.7 Code
Fiction.LiveBench63.9%—
LMArena Longer Query1406—

Writing & Preference Not comparable

GPT-4.5: 56.9 (#134), Kimi K2.7 Code: —

BenchmarkGPT-4.5Kimi K2.7 Code
LMArena Text1417—
LMArena Creative Writing1394—
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LMArena Multi-Turn1444—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 37.2 on the Noometry Index.

Is GPT-4.5 or Kimi K2.7 Code better for coding?

They score almost the same on coding (42.2 vs 42.9); test both on your own repository before choosing.

How many benchmarks do GPT-4.5 and Kimi K2.7 Code share?

5 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper