Noometry

Model comparison

Gemma 2B vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.8 to 29.1 on the Noometry Index.

Last verified . 12 shared benchmarks.

Gemma 2B Google

29.1

Rank #305 Confirmed

Grok 4.6 xAI

56.8

Rank #19 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Grok 4.6 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.6 leads 61.3 to 17.9.
  • Gemma 2B has downloadable open weights; the other is API-only.

Side by side

Gemma 2BGrok 4.6
ProviderGooglexAI
Noometry Index29.156.8
Released2024-02-212026-08-12
WeightsOpenProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked2349

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

Category by category

Coding Grok 4.6 leads

Gemma 2B: 28.9 (#300), Grok 4.6: 58.0 (#14)

BenchmarkGemma 2BGrok 4.6
LMArena Coding10101464
DeepSWE—67.5%
FrontierCode—48%
CursorBench—41.4%
LMArena WebDev—1620
FrontierSWE—25.3%
SciCode—56.5%
WeirdML—67.3%
ALE-Bench—1,508
HumanEval+20.7%—
MBPP+34.1%—

Agentic & Tool Use Not comparable

Gemma 2B: —, Grok 4.6: 39.4 (#25)

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

Reasoning Grok 4.6 leads

Gemma 2B: 17.9 (#275), Grok 4.6: 61.3 (#18)

BenchmarkGemma 2BGrok 4.6
LMArena Hard Prompts9891445
Epoch Capabilities Index93.57156.48
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%
Mystery Game Puzzles—34%
DTBench—97.3%
LMCA—48.5%
BIG-Bench Hard35.2%—
HellaSwag71.4%—
PIQA77.3%—
WinoGrande65.4%—

Math Grok 4.6 leads

Gemma 2B: 27.6 (#237), Grok 4.6: 66.8 (#19)

BenchmarkGemma 2BGrok 4.6
LMArena Math10091416
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
OTIS Mock AIME 2024-2025—99.2%
ProofBench—51%
GSM8K17.7%—

Knowledge Not comparable

Gemma 2B: —, Grok 4.6: 63.3 (#18)

BenchmarkGemma 2BGrok 4.6
GPQA Diamond—94%
SimpleQA Verified—49.3%
LMArena Expert—1463
ARC (AI2) Challenge42.1%—
BoolQ69.4%—
MMLU42.3%—
TriviaQA53.2%—

Multimodal Not comparable

Gemma 2B: —, Grok 4.6: 43.9 (#18)

BenchmarkGemma 2BGrok 4.6
LMArena Vision—1265
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual Grok 4.6 leads

Gemma 2B: 23.1 (#289), Grok 4.6: 53.3 (#67)

BenchmarkGemma 2BGrok 4.6
LMArena Non-English9581422
LMArena Chinese9861479
LMArena Russian9371427
LMArena French—1458
LMArena German—1425
LMArena Japanese—1383
LMArena Korean—1395
LMArena Spanish—1408

Instruction Following Grok 4.6 leads

Gemma 2B: 48.8 (#297), Grok 4.6: 75.6 (#59)

BenchmarkGemma 2BGrok 4.6
LMArena Instruction Following9711431

Long Context Grok 4.6 leads

Gemma 2B: 29.9 (#286), Grok 4.6: 44.4 (#62)

BenchmarkGemma 2BGrok 4.6
LMArena Longer Query9811453

Writing & Preference Grok 4.6 leads

Gemma 2B: 24.1 (#303), Grok 4.6: 62.5 (#77)

BenchmarkGemma 2BGrok 4.6
LMArena Text10021427
LMArena Creative Writing9861430
LMArena Multi-Turn9451422

Frequently asked questions

Is Gemma 2B better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.8 to 29.1 on the Noometry Index.

Is Gemma 2B or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.0 versus 28.9 in the Noometry coding category.

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

12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper