Model comparison

Kimi K2.5 Instant vs Mistral Medium

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 36.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

Kimi K2.5 Instant Moonshot AI

43.6

Rank #89 Confirmed

Mistral Medium Mistral AI

36.3

Rank #218 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 8 categories and Mistral Medium in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K2.5 Instant leads 40.2 to 25.0.

Side by side

Kimi K2.5 Instant and Mistral Medium specifications
Kimi K2.5 InstantMistral Medium
ProviderMoonshot AIMistral AI
Noometry Index43.636.3
Released—2023-12-11
WeightsOpenOpen
Context window—262K
Max output—262K
Input $ / M tokens—$1.50
Output $ / M tokens—$7.50
Results tracked1836

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), Mistral Medium: 34.2 (#243)

Coding benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Coding14841434
FrontierCode—8%
LMArena WebDev1404—
SciCode—40.2%
WeirdML—43.7%
ALE-Bench—763.98

Agentic & Tool Use Not comparable

Kimi K2.5 Instant: —, Mistral Medium: 28.3 (#90)

Agentic & Tool Use benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
Berkeley Function Calling Leaderboard—37.7%

Reasoning Kimi K2.5 Instant leads

Kimi K2.5 Instant: 29.7 (#90), Mistral Medium: 24.0 (#167)

Reasoning benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Hard Prompts14431426
Kagi LLM Benchmark—50%
CritPt—0%
DTBench—75.5%
LMCA—26.1%
Surface Evolver Bench—26.9%

Math Kimi K2.5 Instant leads

Kimi K2.5 Instant: 39.4 (#105), Mistral Medium: 28.1 (#245)

Math benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Math14421408
OTIS Mock AIME 2024-2025—32.2%
ProofBench—9%
MATH Level 5—81.6%
FrontierMath (Feb 2025 set)—0.3%

Knowledge Kimi K2.5 Instant leads

Kimi K2.5 Instant: 40.2 (#123), Mistral Medium: 25.0 (#265)

Knowledge benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Expert14401408
GPQA Diamond—59.5%
Humanity's Last Exam—4.5%
Vectara Hallucination Rate—22.7%

Multimodal Kimi K2.5 Instant leads

Kimi K2.5 Instant: 40.2 (#50), Mistral Medium: 35.3 (#88)

Multimodal benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Vision12541172

Multilingual Too close to call

Kimi K2.5 Instant: 52.0 (#94), Mistral Medium: 52.1 (#91)

Multilingual benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Non-English14061408
LMArena Chinese14491447
LMArena French14031459
LMArena German14131432
LMArena Korean13781380
LMArena Russian14041411
LMArena Spanish14471433
LMArena Japanese—1378

Instruction Following Kimi K2.5 Instant leads

Kimi K2.5 Instant: 75.3 (#65), Mistral Medium: 73.7 (#116)

Instruction Following benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Instruction Following14301398

Long Context Too close to call

Kimi K2.5 Instant: 43.9 (#83), Mistral Medium: 42.9 (#114)

Long Context benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Longer Query14351406

Writing & Preference Too close to call

Kimi K2.5 Instant: 60.6 (#95), Mistral Medium: 60.0 (#103)

Writing & Preference benchmarks
BenchmarkKimi K2.5 InstantMistral Medium
LMArena Text14201424
LMArena Creative Writing13811391
LMArena Multi-Turn14271418
Short-Story Creative Writing—77.3%

Frequently asked questions

Is Kimi K2.5 Instant better than Mistral Medium?

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 36.3 on the Noometry Index.

Is Kimi K2.5 Instant or Mistral Medium better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 34.2 in the Noometry coding category.

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

17 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Mistral Medium has 36.

Related comparisons

Go deeper