Model comparison

Kimi K2.5 Instant vs Mixtral 8x22B

Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 26.7 on the Noometry Index.

Last verified . 16 shared benchmarks.

Kimi K2.5 Instant Moonshot AI

42.9

Rank #92 Confirmed

Mixtral 8x22B Mistral AI

26.7

Rank #330 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 8 categories and Mixtral 8x22B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K2.5 Instant leads 39.5 to 15.1.

Side by side

Kimi K2.5 Instant and Mixtral 8x22B specifications
Kimi K2.5 InstantMixtral 8x22B
ProviderMoonshot AIMistral AI
Noometry Index42.926.7
Released—2024-04-17
WeightsOpenOpen
Context window—64K
Max output—64K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked1834

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: 42.3 (#95), Mixtral 8x22B: 23.8 (#324)

Coding benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Coding14831166
LMArena WebDev1404—
WeirdML—3.2%
BigCodeBench Instruct—40.6%
BigCodeBench Complete—50.2%
HumanEval+—72%
MBPP+—64.3%

Agentic & Tool Use Not comparable

Kimi K2.5 Instant: —, Mixtral 8x22B: 22.8 (#119)

Agentic & Tool Use benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
Cybench—7.5%

Reasoning Kimi K2.5 Instant leads

Kimi K2.5 Instant: 28.5 (#88), Mixtral 8x22B: 19.1 (#246)

Reasoning benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Hard Prompts14431150
DTBench—55.1%
Epoch Capabilities Index—122
ForecastBench—56.3

Math Kimi K2.5 Instant leads

Kimi K2.5 Instant: 36.6 (#105), Mixtral 8x22B: 21.2 (#271)

Math benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Math14431184
Omni-MATH—16.3%
MATH Level 5—24.2%

Knowledge Kimi K2.5 Instant leads

Kimi K2.5 Instant: 39.5 (#121), Mixtral 8x22B: 15.1 (#288)

Knowledge benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Expert14381113
GPQA Diamond—34.1%
MMLU-Pro—46%
GPQA (HELM)—33.4%
MMLU—77.8%

Multimodal Not comparable

Kimi K2.5 Instant: 39.5 (#47), Mixtral 8x22B: —

Multimodal benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Vision1254—

Multilingual Kimi K2.5 Instant leads

Kimi K2.5 Instant: 52.2 (#89), Mixtral 8x22B: 32.9 (#250)

Multilingual benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Non-English14061128
LMArena Chinese14501116
LMArena French14031165
LMArena German14131141
LMArena Korean13781056
LMArena Russian14041158
LMArena Spanish14481150
LMArena Japanese—1037

Instruction Following Kimi K2.5 Instant leads

Kimi K2.5 Instant: 75.5 (#61), Mixtral 8x22B: 57.9 (#261)

Instruction Following benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Instruction Following14301147
IFEval—72.4%

Long Context Kimi K2.5 Instant leads

Kimi K2.5 Instant: 43.8 (#82), Mixtral 8x22B: 34.6 (#242)

Long Context benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Longer Query14351144

Writing & Preference Kimi K2.5 Instant leads

Kimi K2.5 Instant: 60.8 (#91), Mixtral 8x22B: 37.1 (#257)

Writing & Preference benchmarks
BenchmarkKimi K2.5 InstantMixtral 8x22B
LMArena Text14201162
LMArena Creative Writing13791141
LMArena Multi-Turn14271130
WildBench—71.1%

Frequently asked questions

Is Kimi K2.5 Instant better than Mixtral 8x22B?

Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 26.7 on the Noometry Index.

Is Kimi K2.5 Instant or Mixtral 8x22B better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.3 versus 23.8 in the Noometry coding category.

How many benchmarks do Kimi K2.5 Instant and Mixtral 8x22B share?

16 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Mixtral 8x22B has 34.

Related comparisons

Go deeper