Noometry

Model comparison

Gemma 2 9B vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 53.3 to 25.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and GPT-6 Luna in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 9.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 98.9% for GPT-6 Luna.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 9BGPT-6 Luna
ProviderGoogleOpenAI
Noometry Index25.953.3
Released2024-06-242026-09-22
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.50
Results tracked3542

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

Category by category

Coding GPT-6 Luna leads

Gemma 2 9B: 29.4 (#304), GPT-6 Luna: 55.5 (#25)

BenchmarkGemma 2 9BGPT-6 Luna
LMArena Coding11731439
DeepSWE—66.6%
FrontierCode—42.4%
LMArena WebDev—1581
SciCode—54.6%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
ALE-Bench—1,577

Agentic & Tool Use Not comparable

Gemma 2 9B: —, GPT-6 Luna: 33.3 (#54)

BenchmarkGemma 2 9BGPT-6 Luna
APEX-Agents—44.3%
GDP.pdf—23%

Reasoning GPT-6 Luna leads

Gemma 2 9B: 15.9 (#309), GPT-6 Luna: 48.2 (#41)

BenchmarkGemma 2 9BGPT-6 Luna
LMArena Hard Prompts11711411
Epoch Capabilities Index119.83156.28
ARC-AGI-2—59.3%
NYT Connections (extended)—68.7%
ARC-AGI-1—86.7%
CritPt—19.4%
Chess Puzzles—31%
LiveBench Reasoning15.2%—
Mystery Game Puzzles—7%
DTBench—90.1%
LiveBench Data Analysis36.4%—
LMCA—44.5%
LiveBench28.7%—
PIQA83.7%—

Math GPT-6 Luna leads

Gemma 2 9B: 9.9 (#318), GPT-6 Luna: 76.1 (#15)

BenchmarkGemma 2 9BGPT-6 Luna
OTIS Mock AIME 2024-20250.6%98.9%
LMArena Math11831416
FrontierMath (Tiers 1-3)—78.9%
FrontierMath Tier 4—56.1%
ProofBench—64%
LiveBench Math19.8%—
MATH Level 521%—
GSM8K84.9%—

Knowledge GPT-6 Luna leads

Gemma 2 9B: 9.7 (#305), GPT-6 Luna: 57.0 (#41)

BenchmarkGemma 2 9BGPT-6 Luna
GPQA Diamond27.5%90.5%
LMArena Expert11471444
SimpleQA Verified—41.4%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, GPT-6 Luna: 42.4 (#30)

BenchmarkGemma 2 9BGPT-6 Luna
LMArena Vision—1217
Blueprint-Bench 2—31.2%
Furniture Assembly—44.2%

Multilingual GPT-6 Luna leads

Gemma 2 9B: 36.6 (#238), GPT-6 Luna: 50.5 (#117)

BenchmarkGemma 2 9BGPT-6 Luna
LMArena Non-English11881386
LMArena Chinese11851433
LMArena French11901420
LMArena German11861369
LMArena Japanese11441369
LMArena Korean11371360
LMArena Russian12001394
LMArena Spanish12001393

Instruction Following GPT-6 Luna leads

Gemma 2 9B: 57.6 (#269), GPT-6 Luna: 74.3 (#99)

BenchmarkGemma 2 9BGPT-6 Luna
LMArena Instruction Following11781409
LiveBench Instruction Following52.6%—

Long Context GPT-6 Luna leads

Gemma 2 9B: 36.3 (#233), GPT-6 Luna: 43.0 (#111)

BenchmarkGemma 2 9BGPT-6 Luna
LMArena Longer Query11971409

Writing & Preference GPT-6 Luna leads

Gemma 2 9B: 32.1 (#281), GPT-6 Luna: 58.3 (#119)

BenchmarkGemma 2 9BGPT-6 Luna
LMArena Text12071391
LMArena Creative Writing12061363
LMArena Multi-Turn11931396
EQ-Bench Creative Writing841—
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 25.9 on the Noometry Index.

Is Gemma 2 9B or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and GPT-6 Luna share?

20 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-6 Luna has 42.

Related comparisons

Go deeper