Noometry

Model comparison

Gemma 2 9B vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 25.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Grok 4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4 leads 53.8 to 9.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 84% for Grok 4.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 9BGrok 4
ProviderGooglexAI
Noometry Index25.948.1
Released2024-06-242025-07-09
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3548

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

Category by category

Coding Grok 4 leads

Gemma 2 9B: 29.4 (#304), Grok 4: 50.3 (#46)

BenchmarkGemma 2 9BGrok 4
LMArena Coding11731408
Aider Polyglot—79.6%
WeirdML—45.7%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—

Agentic & Tool Use Not comparable

Gemma 2 9B: —, Grok 4: 32.3 (#68)

BenchmarkGemma 2 9BGrok 4
Terminal-Bench—27.2%
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
LMArena Search—1142
METR Time Horizons—66.6%

Reasoning Grok 4 leads

Gemma 2 9B: 15.9 (#309), Grok 4: 36.7 (#65)

BenchmarkGemma 2 9BGrok 4
LMArena Hard Prompts11711409
Epoch Capabilities Index119.83146.44
ARC-AGI-2—16%
SimpleBench—60.5%
Kagi LLM Benchmark—73.6%
ARC-AGI-1—66.7%
Chess Puzzles—28%
LiveBench Reasoning15.2%—
LiveBench Data Analysis36.4%—
ForecastBench—60.9
LiveBench28.7%—
PIQA83.7%—

Math Grok 4 leads

Gemma 2 9B: 9.9 (#318), Grok 4: 48.4 (#64)

BenchmarkGemma 2 9BGrok 4
OTIS Mock AIME 2024-20250.6%84%
LMArena Math11831422
Omni-MATH—60.3%
LiveBench Math19.8%—
MATH Level 521%—
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%
GSM8K84.9%—

Knowledge Grok 4 leads

Gemma 2 9B: 9.7 (#305), Grok 4: 53.8 (#55)

BenchmarkGemma 2 9BGrok 4
GPQA Diamond27.5%87%
LMArena Expert11471415
MMLU-Pro—85.1%
Confabulations—12.4%
GPQA (HELM)—72.7%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, Grok 4: 33.7 (#94)

BenchmarkGemma 2 9BGrok 4
LMArena Vision—1210
GeoBench—45%

Multilingual Grok 4 leads

Gemma 2 9B: 36.6 (#238), Grok 4: 51.8 (#103)

BenchmarkGemma 2 9BGrok 4
LMArena Non-English11881403
LMArena Chinese11851427
LMArena French11901418
LMArena German11861429
LMArena Japanese11441394
LMArena Korean11371377
LMArena Russian12001410
LMArena Spanish12001420

Instruction Following Grok 4 leads

Gemma 2 9B: 57.6 (#269), Grok 4: 79.2 (#5)

BenchmarkGemma 2 9BGrok 4
LMArena Instruction Following11781387
LiveBench Instruction Following52.6%—
IFEval—94.9%

Long Context Grok 4 leads

Gemma 2 9B: 36.3 (#233), Grok 4: 63.1 (#4)

BenchmarkGemma 2 9BGrok 4
LMArena Longer Query11971409
Fiction.LiveBench—94.4%

Writing & Preference Grok 4 leads

Gemma 2 9B: 32.1 (#281), Grok 4: 58.5 (#116)

BenchmarkGemma 2 9BGrok 4
LMArena Text12071411
LMArena Creative Writing12061397
LMArena Multi-Turn11931416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing841—
WildBench—79.7%
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Grok 4 share?

20 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper