Noometry

Model comparison

Kimi K2.5 Instant vs Phi-4

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 31.2 on the Noometry Index.

Last verified . 16 shared benchmarks.

Kimi K2.5 Instant Moonshot AI

43.6

Rank #89 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Kimi K2.5 Instant leads 60.6 to 40.5.

Side by side

Kimi K2.5 InstantPhi-4
ProviderMoonshot AIMicrosoft
Noometry Index43.631.2
Released—2024-12-11
WeightsOpenOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.07
Output $ / M tokens—$0.14
Results tracked1837

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

Category by category

Coding Kimi K2.5 Instant leads

Kimi K2.5 Instant: 42.6 (#97), Phi-4: 34.4 (#239)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Coding14841231
LMArena WebDev1404—
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%

Agentic & Tool Use Not comparable

Kimi K2.5 Instant: —, Phi-4: 22.8 (#128)

BenchmarkKimi K2.5 InstantPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Kimi K2.5 Instant leads

Kimi K2.5 Instant: 29.7 (#90), Phi-4: 17.7 (#291)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Hard Prompts14431220
Chess Puzzles—1%
LiveBench Reasoning—47.8%
LiveBench Data Analysis—45.2%
Epoch Capabilities Index—130.42
LiveBench—41.6%

Math Kimi K2.5 Instant leads

Kimi K2.5 Instant: 39.4 (#105), Phi-4: 20.8 (#285)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Math14421246
OTIS Mock AIME 2024-2025—13.8%
LiveBench Math—42%
MATH Level 5—64.9%

Knowledge Kimi K2.5 Instant leads

Kimi K2.5 Instant: 40.2 (#123), Phi-4: 32.6 (#209)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Expert14401203
GPQA Diamond—56.1%
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multimodal Not comparable

Kimi K2.5 Instant: 40.2 (#50), Phi-4: —

BenchmarkKimi K2.5 InstantPhi-4
LMArena Vision1254—

Multilingual Kimi K2.5 Instant leads

Kimi K2.5 Instant: 52.0 (#94), Phi-4: 37.2 (#237)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Non-English14061197
LMArena Chinese14491212
LMArena French14031224
LMArena German14131222
LMArena Korean13781151
LMArena Russian14041209
LMArena Spanish14471234
LMArena Japanese—1158

Instruction Following Kimi K2.5 Instant leads

Kimi K2.5 Instant: 75.3 (#65), Phi-4: 60.4 (#251)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Instruction Following14301201
LiveBench Instruction Following—58.4%

Long Context Kimi K2.5 Instant leads

Kimi K2.5 Instant: 43.9 (#83), Phi-4: 36.9 (#226)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Longer Query14351217

Writing & Preference Kimi K2.5 Instant leads

Kimi K2.5 Instant: 60.6 (#95), Phi-4: 40.5 (#244)

BenchmarkKimi K2.5 InstantPhi-4
LMArena Text14201217
LMArena Creative Writing13811182
LMArena Multi-Turn14271206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is Kimi K2.5 Instant better than Phi-4?

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 31.2 on the Noometry Index.

Is Kimi K2.5 Instant or Phi-4 better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 34.4 in the Noometry coding category.

How many benchmarks do Kimi K2.5 Instant and Phi-4 share?

16 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper