Model comparison

Kimi K2 Thinking Turbo vs Step 3.7 Flash

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 37.3 on the Noometry Index.

Last verified . 0 shared benchmarks.

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • The widest gap is in reasoning, where Kimi K2 Thinking Turbo leads 32.5 to 21.6.

Side by side

Kimi K2 Thinking Turbo and Step 3.7 Flash specifications
Kimi K2 Thinking TurboStep 3.7 Flash
ProviderMoonshot AIStepFun
Noometry Index45.837.3
Released2025-11-062026-05-29
WeightsOpenOpen
Context window—256K
Max output—256K
Input $ / M tokens—$0.18
Output $ / M tokens—$1.11
Results tracked215

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

Category by category

Coding Step 3.7 Flash leads

Kimi K2 Thinking Turbo: 38.4 (#178), Step 3.7 Flash: 40.0 (#150)

Coding benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
LMArena WebDev1322—
SciCode—40%
LMArena Coding1454—
ALE-Bench—694.12

Reasoning Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 32.5 (#75), Step 3.7 Flash: 21.6 (#219)

Reasoning benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
NYT Connections (extended)—39.7%
CritPt—2.3%
Chess Puzzles20%—
LMArena Hard Prompts1428—

Math Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 47.4 (#68), Step 3.7 Flash: 42.9 (#82)

Math benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-202583.1%—
LMArena Math1429—

Knowledge Not comparable

Kimi K2 Thinking Turbo: 50.9 (#69), Step 3.7 Flash: —

Knowledge benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
GPQA Diamond84.2%—
LMArena Expert1439—

Multilingual Not comparable

Kimi K2 Thinking Turbo: 51.4 (#109), Step 3.7 Flash: —

Multilingual benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
LMArena Non-English1398—
LMArena Chinese1456—
LMArena French1425—
LMArena German1390—
LMArena Japanese1357—
LMArena Korean1330—
LMArena Russian1391—
LMArena Spanish1406—

Instruction Following Not comparable

Kimi K2 Thinking Turbo: 74.0 (#109), Step 3.7 Flash: —

Instruction Following benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
LMArena Instruction Following1403—

Long Context Not comparable

Kimi K2 Thinking Turbo: 43.2 (#102), Step 3.7 Flash: —

Long Context benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
LMArena Longer Query1415—

Writing & Preference Not comparable

Kimi K2 Thinking Turbo: 60.0 (#104), Step 3.7 Flash: —

Writing & Preference benchmarks
BenchmarkKimi K2 Thinking TurboStep 3.7 Flash
LMArena Text1415—
LMArena Creative Writing1374—
LMArena Multi-Turn1414—

Frequently asked questions

Is Kimi K2 Thinking Turbo better than Step 3.7 Flash?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 37.3 on the Noometry Index.

Is Kimi K2 Thinking Turbo or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 38.4 in the Noometry coding category.

How many benchmarks do Kimi K2 Thinking Turbo and Step 3.7 Flash share?

0 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper