Model comparison

Gemma 2B vs Kimi K2.5 Instant

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 29.6 on the Noometry Index.

Last verified . 11 shared benchmarks.

Gemma 2B Google

29.6

Rank #307 Confirmed

Kimi K2.5 Instant Moonshot AI

43.6

Rank #89 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Kimi K2.5 Instant in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Kimi K2.5 Instant leads 60.6 to 24.0.

Side by side

Gemma 2B and Kimi K2.5 Instant specifications
Gemma 2BKimi K2.5 Instant
ProviderGoogleMoonshot AI
Noometry Index29.643.6
Released2024-02-21—
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2318

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

Category by category

Coding Kimi K2.5 Instant leads

Gemma 2B: 29.4 (#305), Kimi K2.5 Instant: 42.6 (#97)

Coding benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Coding10101484
LMArena WebDev—1404
HumanEval+20.7%—
MBPP+34.1%—

Reasoning Kimi K2.5 Instant leads

Gemma 2B: 18.8 (#275), Kimi K2.5 Instant: 29.7 (#90)

Reasoning benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Hard Prompts9891443
BIG-Bench Hard35.2%—
Epoch Capabilities Index94.2—
HellaSwag71.4%—
PIQA77.3%—
WinoGrande65.4%—

Math Kimi K2.5 Instant leads

Gemma 2B: 30.0 (#239), Kimi K2.5 Instant: 39.4 (#105)

Math benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Math10091442
GSM8K17.7%—

Knowledge Not comparable

Gemma 2B: —, Kimi K2.5 Instant: 40.2 (#123)

Knowledge benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Expert—1440
ARC (AI2) Challenge42.1%—
BoolQ69.4%—
MMLU42.3%—
TriviaQA53.2%—

Multimodal Not comparable

Gemma 2B: —, Kimi K2.5 Instant: 40.2 (#50)

Multimodal benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Vision—1254

Multilingual Kimi K2.5 Instant leads

Gemma 2B: 23.0 (#294), Kimi K2.5 Instant: 52.0 (#94)

Multilingual benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Non-English9581406
LMArena Chinese9861449
LMArena Russian9371404
LMArena French—1403
LMArena German—1413
LMArena Korean—1378
LMArena Spanish—1447

Instruction Following Kimi K2.5 Instant leads

Gemma 2B: 48.5 (#302), Kimi K2.5 Instant: 75.3 (#65)

Instruction Following benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Instruction Following9701430

Long Context Kimi K2.5 Instant leads

Gemma 2B: 29.9 (#291), Kimi K2.5 Instant: 43.9 (#83)

Long Context benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Longer Query9811435

Writing & Preference Kimi K2.5 Instant leads

Gemma 2B: 24.0 (#308), Kimi K2.5 Instant: 60.6 (#95)

Writing & Preference benchmarks
BenchmarkGemma 2BKimi K2.5 Instant
LMArena Text10021420
LMArena Creative Writing9871381
LMArena Multi-Turn9451427

Frequently asked questions

Is Gemma 2B better than Kimi K2.5 Instant?

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 29.6 on the Noometry Index.

Is Gemma 2B or Kimi K2.5 Instant better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2B and Kimi K2.5 Instant share?

11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Kimi K2.5 Instant has 18.

Related comparisons

Go deeper