Model comparison

Kimi K2 Thinking Turbo vs Step 3.5 Flash

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 42.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Step 3.5 Flash StepFun

42.3

Rank #116 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 7 categories and Step 3.5 Flash in 1 category; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 39.6.

Side by side

Kimi K2 Thinking Turbo and Step 3.5 Flash specifications
Kimi K2 Thinking TurboStep 3.5 Flash
ProviderMoonshot AIStepFun
Noometry Index45.842.3
Released2025-11-062026-01-29
WeightsOpenOpen
Context window—256K
Max output—256K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.30
Results tracked2119

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

Category by category

Coding Step 3.5 Flash leads

Kimi K2 Thinking Turbo: 38.4 (#178), Step 3.5 Flash: 42.4 (#105)

Coding benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Coding14541436
LMArena WebDev1322—

Reasoning Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 32.5 (#75), Step 3.5 Flash: 22.2 (#202)

Reasoning benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Hard Prompts14281411
NYT Connections (extended)—28.4%
Chess Puzzles20%—

Math Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 47.4 (#68), Step 3.5 Flash: 42.6 (#84)

Math benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Math14291408
MathArena Final-Answer Competitions—66.8%
OTIS Mock AIME 2024-202583.1%—

Knowledge Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 50.9 (#69), Step 3.5 Flash: 39.6 (#132)

Knowledge benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Expert14391421
GPQA Diamond84.2%—

Multilingual Too close to call

Kimi K2 Thinking Turbo: 51.4 (#109), Step 3.5 Flash: 50.5 (#119)

Multilingual benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Non-English13981385
LMArena Chinese14561447
LMArena French14251421
LMArena German13901405
LMArena Japanese13571354
LMArena Korean13301352
LMArena Russian13911385
LMArena Spanish14061419

Instruction Following Too close to call

Kimi K2 Thinking Turbo: 74.0 (#109), Step 3.5 Flash: 73.1 (#124)

Instruction Following benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Instruction Following14031385

Long Context Too close to call

Kimi K2 Thinking Turbo: 43.2 (#102), Step 3.5 Flash: 42.8 (#117)

Long Context benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Longer Query14151402

Writing & Preference Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 60.0 (#104), Step 3.5 Flash: 58.8 (#113)

Writing & Preference benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.5 Flash
LMArena Text14151403
LMArena Creative Writing13741357
LMArena Multi-Turn14141405

Frequently asked questions

Is Kimi K2 Thinking Turbo better than Step 3.5 Flash?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 42.3 on the Noometry Index.

Is Kimi K2 Thinking Turbo or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 38.4 in the Noometry coding category.

How many benchmarks do Kimi K2 Thinking Turbo and Step 3.5 Flash share?

17 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper