Noometry

Model comparison

Gemma 2 9B vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.9 to 25.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.6 leads 67.0 to 9.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 99.2% for Grok 4.6.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 9BGrok 4.6
ProviderGooglexAI
Noometry Index25.956.9
Released2024-06-242026-08-12
WeightsOpenProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3549

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

Category by category

Coding Grok 4.6 leads

Gemma 2 9B: 29.4 (#304), Grok 4.6: 58.5 (#16)

BenchmarkGemma 2 9BGrok 4.6
LMArena Coding11731465
DeepSWE—67.5%
FrontierCode—48%
CursorBench—41.4%
LMArena WebDev—1617
FrontierSWE—25.3%
SciCode—56.5%
WeirdML—67.3%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
ALE-Bench—1,508

Agentic & Tool Use Not comparable

Gemma 2 9B: —, Grok 4.6: 39.4 (#27)

BenchmarkGemma 2 9BGrok 4.6
APEX-Agents—65.3%
GDP.pdf—17.2%
Vending-Bench 2—9,047

Reasoning Grok 4.6 leads

Gemma 2 9B: 15.9 (#309), Grok 4.6: 61.4 (#20)

BenchmarkGemma 2 9BGrok 4.6
LMArena Hard Prompts11711447
Epoch Capabilities Index119.83156.44
ARC-AGI-2—67.1%
SimpleBench—75.9%
NYT Connections (extended)—80%
ARC-AGI-1—87.5%
CritPt—19.7%
Chess Puzzles—40%
EBR-Bench—30.5%
LiveBench Reasoning15.2%—
Mystery Game Puzzles—34%
DTBench—97.3%
LiveBench Data Analysis36.4%—
LMCA—48.5%
LiveBench28.7%—
PIQA83.7%—

Math Grok 4.6 leads

Gemma 2 9B: 9.9 (#318), Grok 4.6: 67.0 (#24)

BenchmarkGemma 2 9BGrok 4.6
OTIS Mock AIME 2024-20250.6%99.2%
LMArena Math11831423
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
ProofBench—51%
LiveBench Math19.8%—
MATH Level 521%—
GSM8K84.9%—

Knowledge Grok 4.6 leads

Gemma 2 9B: 9.7 (#305), Grok 4.6: 63.3 (#20)

BenchmarkGemma 2 9BGrok 4.6
GPQA Diamond27.5%94%
LMArena Expert11471467
SimpleQA Verified—49.3%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, Grok 4.6: 43.6 (#23)

BenchmarkGemma 2 9BGrok 4.6
LMArena Vision—1263
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual Grok 4.6 leads

Gemma 2 9B: 36.6 (#238), Grok 4.6: 53.0 (#74)

BenchmarkGemma 2 9BGrok 4.6
LMArena Non-English11881420
LMArena Chinese11851480
LMArena French11901461
LMArena German11861431
LMArena Japanese11441376
LMArena Korean11371397
LMArena Russian12001422
LMArena Spanish12001404

Instruction Following Grok 4.6 leads

Gemma 2 9B: 57.6 (#269), Grok 4.6: 75.4 (#63)

BenchmarkGemma 2 9BGrok 4.6
LMArena Instruction Following11781431
LiveBench Instruction Following52.6%—

Long Context Grok 4.6 leads

Gemma 2 9B: 36.3 (#233), Grok 4.6: 44.5 (#66)

BenchmarkGemma 2 9BGrok 4.6
LMArena Longer Query11971454

Writing & Preference Grok 4.6 leads

Gemma 2 9B: 32.1 (#281), Grok 4.6: 62.3 (#80)

BenchmarkGemma 2 9BGrok 4.6
LMArena Text12071428
LMArena Creative Writing12061428
LMArena Multi-Turn11931425
EQ-Bench Creative Writing841—
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Grok 4.6 share?

20 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper