Noometry

Model comparison

Gemma 2 9B vs Kimi K3

Kimi K3 is the stronger model overall, scoring 59.5 to 25.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Kimi K3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K3 leads 74.2 to 9.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 97.2% for Kimi K3.

Side by side

Gemma 2 9BKimi K3
ProviderGoogleMoonshot AI
Noometry Index25.959.5
Released2024-06-242026-07-16
WeightsOpenOpen
Context window—1.05M
Max output—1.05M
Input $ / M tokens—$3
Output $ / M tokens—$15
Results tracked3553

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

Category by category

Coding Kimi K3 leads

Gemma 2 9B: 29.4 (#304), Kimi K3: 61.0 (#10)

BenchmarkGemma 2 9BKimi K3
LMArena Coding11731508
DeepSWE—68.5%
FrontierCode—44.2%
LMArena WebDev—1654
FrontierSWE—25.9%
SciCode—59.5%
WeirdML—82.6%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
ALE-Bench—1,524

Agentic & Tool Use Not comparable

Gemma 2 9B: —, Kimi K3: 41.8 (#20)

BenchmarkGemma 2 9BKimi K3
APEX-Agents—50.6%
τ²-bench Banking—37.1%
PostTrainBench—32%
GBAEval—48.3%
GDP.pdf—19%
Vending-Bench 2—5,165

Reasoning Kimi K3 leads

Gemma 2 9B: 15.9 (#309), Kimi K3: 63.0 (#17)

BenchmarkGemma 2 9BKimi K3
LMArena Hard Prompts11711496
Epoch Capabilities Index119.83157.45
ARC-AGI-2—60.4%
SimpleBench—60.7%
NYT Connections (extended)—93.6%
ARC-AGI-1—94.5%
CritPt—23.4%
Chess Puzzles—39%
LiveBench Reasoning15.2%—
Mystery Game Puzzles—26%
DTBench—91.2%
LiveBench Data Analysis36.4%—
LMCA—52.7%
Surface Evolver Bench—95%
ForecastBench—61.1
LiveBench28.7%—
PIQA83.7%—

Math Kimi K3 leads

Gemma 2 9B: 9.9 (#318), Kimi K3: 74.2 (#16)

BenchmarkGemma 2 9BKimi K3
OTIS Mock AIME 2024-20250.6%97.2%
LMArena Math11831491
FrontierMath (Tiers 1-3)—72.2%
FrontierMath Tier 4—39%
MathArena Final-Answer Competitions—87.8%
ProofBench—87%
LiveBench Math19.8%—
MATH Level 521%—
GSM8K84.9%—

Knowledge Kimi K3 leads

Gemma 2 9B: 9.7 (#305), Kimi K3: 63.2 (#21)

BenchmarkGemma 2 9BKimi K3
GPQA Diamond27.5%93.1%
LMArena Expert11471521
SimpleQA Verified—50.6%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, Kimi K3: 37.8 (#70)

BenchmarkGemma 2 9BKimi K3
Blueprint-Bench 2—29.5%
Furniture Assembly—34.2%

Multilingual Kimi K3 leads

Gemma 2 9B: 36.6 (#238), Kimi K3: 56.3 (#21)

BenchmarkGemma 2 9BKimi K3
LMArena Non-English11881466
LMArena Chinese11851529
LMArena French11901491
LMArena German11861488
LMArena Japanese11441487
LMArena Korean11371458
LMArena Russian12001482
LMArena Spanish12001472

Instruction Following Kimi K3 leads

Gemma 2 9B: 57.6 (#269), Kimi K3: 77.7 (#14)

BenchmarkGemma 2 9BKimi K3
LMArena Instruction Following11781483
LiveBench Instruction Following52.6%—

Long Context Kimi K3 leads

Gemma 2 9B: 36.3 (#233), Kimi K3: 45.8 (#29)

BenchmarkGemma 2 9BKimi K3
LMArena Longer Query11971494

Writing & Preference Kimi K3 leads

Gemma 2 9B: 32.1 (#281), Kimi K3: 76.6 (#4)

BenchmarkGemma 2 9BKimi K3
LMArena Text12071476
LMArena Creative Writing12061454
EQ-Bench Creative Writing8412082
LMArena Multi-Turn11931488
EQ-Bench 4—1339
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Kimi K3 share?

21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper