Noometry

Model comparison

Gemma 3 12B vs Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 31.8 on the Noometry Index.

Last verified . 15 shared benchmarks.

Gemma 3 12B Google

31.8

Rank #255 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.4

Rank #63 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2 Thinking Turbo leads 45.5 to 21.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 83.1% for Kimi K2 Thinking Turbo.

Side by side

Gemma 3 12BKimi K2 Thinking Turbo
ProviderGoogleMoonshot AI
Noometry Index31.845.4
Released2025-03-122025-11-06
WeightsOpenOpen
Context window131K—
Max output8K—
Input $ / M tokens$0.05—
Output $ / M tokens$0.15—
Results tracked2421

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

Category by category

Coding Kimi K2 Thinking Turbo leads

Gemma 3 12B: 31.2 (#276), Kimi K2 Thinking Turbo: 38.1 (#166)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
LMArena Coding12811454
LMArena WebDev—1322
SciCode17.4%—

Agentic & Tool Use Not comparable

Gemma 3 12B: 25.3 (#101), Kimi K2 Thinking Turbo: —

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
Berkeley Function Calling Leaderboard30.4%—

Reasoning Kimi K2 Thinking Turbo leads

Gemma 3 12B: 15.2 (#307), Kimi K2 Thinking Turbo: 31.4 (#72)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
Chess Puzzles0%20%
LMArena Hard Prompts13091428
CritPt0%—
DTBench48.8%—
LMCA4.5%—
Epoch Capabilities Index123.49—

Math Kimi K2 Thinking Turbo leads

Gemma 3 12B: 21.0 (#273), Kimi K2 Thinking Turbo: 45.5 (#62)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
OTIS Mock AIME 2024-202516.7%83.1%
LMArena Math13071429

Knowledge Kimi K2 Thinking Turbo leads

Gemma 3 12B: 26.5 (#250), Kimi K2 Thinking Turbo: 50.9 (#64)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
GPQA Diamond39.5%84.2%
LMArena Expert12481439
Vectara Hallucination Rate4.4%—

Multimodal Not comparable

Gemma 3 12B: —, Kimi K2 Thinking Turbo: —

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
MindCube46.7%—

Multilingual Kimi K2 Thinking Turbo leads

Gemma 3 12B: 45.9 (#160), Kimi K2 Thinking Turbo: 51.6 (#104)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
LMArena Non-English13181398
LMArena German13701390
LMArena Russian13351390
LMArena Chinese—1457
LMArena French—1425
LMArena Japanese—1356
LMArena Korean—1329
LMArena Spanish—1407

Instruction Following Kimi K2 Thinking Turbo leads

Gemma 3 12B: 68.8 (#179), Kimi K2 Thinking Turbo: 74.2 (#103)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
LMArena Instruction Following12991403

Long Context Kimi K2 Thinking Turbo leads

Gemma 3 12B: 40.0 (#157), Kimi K2 Thinking Turbo: 43.2 (#99)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
LMArena Longer Query13171415

Writing & Preference Kimi K2 Thinking Turbo leads

Gemma 3 12B: 47.7 (#205), Kimi K2 Thinking Turbo: 60.2 (#99)

BenchmarkGemma 3 12BKimi K2 Thinking Turbo
LMArena Text13341415
LMArena Creative Writing13311373
LMArena Multi-Turn13341414
EQ-Bench Creative Writing1126—

Frequently asked questions

Is Gemma 3 12B better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 31.8 on the Noometry Index.

Is Gemma 3 12B or Kimi K2 Thinking Turbo better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 31.2 in the Noometry coding category.

How many benchmarks do Gemma 3 12B and Kimi K2 Thinking Turbo share?

15 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper