Noometry

Model comparison

Gemma 2 9B vs Kimi K2.6

Kimi K2.6 is the stronger model overall, scoring 47.7 to 25.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Kimi K2.6 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.6 leads 57.0 to 9.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 96.1% for Kimi K2.6.

Side by side

Gemma 2 9BKimi K2.6
ProviderGoogleMoonshot AI
Noometry Index25.947.7
Released2024-06-242026-04-20
WeightsOpenOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.95
Output $ / M tokens—$4
Results tracked3551

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

Category by category

Coding Kimi K2.6 leads

Gemma 2 9B: 29.4 (#304), Kimi K2.6: 50.7 (#43)

BenchmarkGemma 2 9BKimi K2.6
LMArena Coding11731488
SWE-bench Verified—76.7%
LMArena WebDev—1509
SciCode—53.5%
WeirdML—55.9%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
ALE-Bench—1,093

Agentic & Tool Use Not comparable

Gemma 2 9B: —, Kimi K2.6: 21.9 (#137)

BenchmarkGemma 2 9BKimi K2.6
OSWorld 2.0—4.6%
ExploitBench—18.4%
GBAEval—0.9%
GDP.pdf—12%
Vending-Bench 2—6,205

Reasoning Kimi K2.6 leads

Gemma 2 9B: 15.9 (#309), Kimi K2.6: 40.5 (#55)

BenchmarkGemma 2 9BKimi K2.6
LMArena Hard Prompts11711470
Epoch Capabilities Index119.83151.05
NYT Connections (extended)—87.2%
CritPt—8%
Chess Puzzles—26%
EBR-Bench—2.4%
LiveBench Reasoning15.2%—
Mystery Game Puzzles—18%
DTBench—90.9%
LiveBench Data Analysis36.4%—
LMCA—37.3%
LiveBench28.7%—
PIQA83.7%—

Math Kimi K2.6 leads

Gemma 2 9B: 9.9 (#318), Kimi K2.6: 57.0 (#41)

BenchmarkGemma 2 9BKimi K2.6
OTIS Mock AIME 2024-20250.6%96.1%
LMArena Math11831475
FrontierMath (Tiers 1-3)—57.2%
FrontierMath Tier 4—25.6%
MathArena Final-Answer Competitions—72.9%
ProofBench—16%
LiveBench Math19.8%—
MATH Level 521%—
FrontierMath (Feb 2025 set)—39%
FrontierMath Tier 4 (v1)—14.6%
GSM8K84.9%—

Knowledge Kimi K2.6 leads

Gemma 2 9B: 9.7 (#305), Kimi K2.6: 54.0 (#54)

BenchmarkGemma 2 9BKimi K2.6
GPQA Diamond27.5%90.8%
LMArena Expert11471491
SimpleQA Verified—34.9%
Vectara Hallucination Rate—10.8%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, Kimi K2.6: 31.6 (#103)

BenchmarkGemma 2 9BKimi K2.6
LMArena Vision—1283
Blueprint-Bench 2—3.9%
Furniture Assembly—21.7%
LMArena Document—1451

Multilingual Kimi K2.6 leads

Gemma 2 9B: 36.6 (#238), Kimi K2.6: 54.9 (#37)

BenchmarkGemma 2 9BKimi K2.6
LMArena Non-English11881446
LMArena Chinese11851521
LMArena French11901471
LMArena German11861450
LMArena Japanese11441443
LMArena Korean11371427
LMArena Russian12001446
LMArena Spanish12001464

Instruction Following Kimi K2.6 leads

Gemma 2 9B: 57.6 (#269), Kimi K2.6: 76.3 (#43)

BenchmarkGemma 2 9BKimi K2.6
LMArena Instruction Following11781451
LiveBench Instruction Following52.6%—

Long Context Kimi K2.6 leads

Gemma 2 9B: 36.3 (#233), Kimi K2.6: 44.9 (#52)

BenchmarkGemma 2 9BKimi K2.6
LMArena Longer Query11971468

Writing & Preference Kimi K2.6 leads

Gemma 2 9B: 32.1 (#281), Kimi K2.6: 68.5 (#26)

BenchmarkGemma 2 9BKimi K2.6
LMArena Text12071455
LMArena Creative Writing12061434
EQ-Bench Creative Writing8411725
LMArena Multi-Turn11931453
EQ-Bench 4—1202
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Kimi K2.6 share?

21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper