Noometry

Model comparison

Kimi K2.5 Instant vs Kimi K3

Kimi K3 is the stronger model overall, scoring 59.5 to 43.6 on the Noometry Index.

Last verified . 17 shared benchmarks.

Kimi K2.5 Instant Moonshot AI

43.6

Rank #89 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 1 category and Kimi K3 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K3 leads 74.2 to 39.4.

Side by side

Kimi K2.5 InstantKimi K3
ProviderMoonshot AIMoonshot AI
Noometry Index43.659.5
Released—2026-07-16
WeightsOpenOpen
Context window—1.05M
Max output—1.05M
Input $ / M tokens—$3
Output $ / M tokens—$15
Results tracked1853

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

Category by category

Coding Kimi K3 leads

Kimi K2.5 Instant: 42.6 (#97), Kimi K3: 61.0 (#10)

BenchmarkKimi K2.5 InstantKimi K3
LMArena WebDev14041654
LMArena Coding14841508
DeepSWE—68.5%
FrontierCode—44.2%
FrontierSWE—25.9%
SciCode—59.5%
WeirdML—82.6%
ALE-Bench—1,524

Agentic & Tool Use Not comparable

Kimi K2.5 Instant: —, Kimi K3: 41.8 (#20)

BenchmarkKimi K2.5 InstantKimi K3
APEX-Agents—50.6%
τ²-bench Banking—37.1%
PostTrainBench—32%
GBAEval—48.3%
GDP.pdf—19%
Vending-Bench 2—5,165

Reasoning Kimi K3 leads

Kimi K2.5 Instant: 29.7 (#90), Kimi K3: 63.0 (#17)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Hard Prompts14431496
ARC-AGI-2—60.4%
SimpleBench—60.7%
NYT Connections (extended)—93.6%
ARC-AGI-1—94.5%
CritPt—23.4%
Chess Puzzles—39%
Mystery Game Puzzles—26%
DTBench—91.2%
LMCA—52.7%
Surface Evolver Bench—95%
Epoch Capabilities Index—157.45
ForecastBench—61.1

Math Kimi K3 leads

Kimi K2.5 Instant: 39.4 (#105), Kimi K3: 74.2 (#16)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Math14421491
FrontierMath (Tiers 1-3)—72.2%
FrontierMath Tier 4—39%
MathArena Final-Answer Competitions—87.8%
OTIS Mock AIME 2024-2025—97.2%
ProofBench—87%

Knowledge Kimi K3 leads

Kimi K2.5 Instant: 40.2 (#123), Kimi K3: 63.2 (#21)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Expert14401521
GPQA Diamond—93.1%
SimpleQA Verified—50.6%

Multimodal Kimi K2.5 Instant leads

Kimi K2.5 Instant: 40.2 (#50), Kimi K3: 37.8 (#70)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Vision1254—
Blueprint-Bench 2—29.5%
Furniture Assembly—34.2%

Multilingual Kimi K3 leads

Kimi K2.5 Instant: 52.0 (#94), Kimi K3: 56.3 (#21)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Non-English14061466
LMArena Chinese14491529
LMArena French14031491
LMArena German14131488
LMArena Korean13781458
LMArena Russian14041482
LMArena Spanish14471472
LMArena Japanese—1487

Instruction Following Kimi K3 leads

Kimi K2.5 Instant: 75.3 (#65), Kimi K3: 77.7 (#14)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Instruction Following14301483

Long Context Kimi K3 leads

Kimi K2.5 Instant: 43.9 (#83), Kimi K3: 45.8 (#29)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Longer Query14351494

Writing & Preference Kimi K3 leads

Kimi K2.5 Instant: 60.6 (#95), Kimi K3: 76.6 (#4)

BenchmarkKimi K2.5 InstantKimi K3
LMArena Text14201476
LMArena Creative Writing13811454
LMArena Multi-Turn14271488
EQ-Bench Creative Writing—2082
EQ-Bench 4—1339

Frequently asked questions

Is Kimi K2.5 Instant better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 43.6 on the Noometry Index.

Is Kimi K2.5 Instant or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 42.6 in the Noometry coding category.

How many benchmarks do Kimi K2.5 Instant and Kimi K3 share?

17 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper