Noometry

Model comparison

Gemma 2 27B vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 45.1 to 29.2 on the Noometry Index.

Last verified . 13 shared benchmarks.

Gemma 2 27B Google

29.2

Rank #302 Confirmed

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Gemma 2 27B 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 35.6 to 10.0.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 8K.
  • Gemma 2 27B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 27BGPT-6 Luna
ProviderGoogleOpenAI
Noometry Index29.245.1
Released2024-06-242026-09-22
WeightsOpenProprietary
Context window8K1.05M
Max output2K128K
Input $ / M tokens$0.65$0.10
Output $ / M tokens$0.65$0.50
Results tracked3418

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

Category by category

Coding GPT-6 Luna leads

Gemma 2 27B: 33.5 (#243), GPT-6 Luna: 54.7 (#24)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Coding12111448
DeepSWE—66.6%
FrontierCode—42.4%
LMArena WebDev—1583
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
BigCodeBench Complete52.5%—

Reasoning GPT-6 Luna leads

Gemma 2 27B: 14.8 (#313), GPT-6 Luna: 31.7 (#68)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Hard Prompts11991415
NYT Connections (extended)—68.7%
LiveBench Reasoning28.1%—
DTBench48%—
LiveBench Data Analysis47.9%—
LMCA7.1%—
Epoch Capabilities Index122.06—
LiveBench38.2%—

Math GPT-6 Luna leads

Gemma 2 27B: 10.0 (#306), GPT-6 Luna: 35.6 (#140)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Math12121396
OTIS Mock AIME 2024-20251.4%—
LiveBench Math26.5%—
MATH Level 527.9%—

Knowledge GPT-6 Luna leads

Gemma 2 27B: 18.9 (#275), GPT-6 Luna: 40.1 (#110)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Expert11721458
GPQA Diamond36.5%—
Confabulations27.1%—
MMLU75.7%—

Multimodal Not comparable

Gemma 2 27B: —, GPT-6 Luna: 42.0 (#27)

BenchmarkGemma 2 27BGPT-6 Luna
Furniture Assembly—44.2%

Multilingual GPT-6 Luna leads

Gemma 2 27B: 38.8 (#221), GPT-6 Luna: 51.0 (#111)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Non-English12171390
LMArena Chinese12211425
LMArena Russian12341392
LMArena Spanish12281416
LMArena French1246—
LMArena German1209—
LMArena Japanese1175—
LMArena Korean1174—

Instruction Following GPT-6 Luna leads

Gemma 2 27B: 60.7 (#244), GPT-6 Luna: 74.7 (#85)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Instruction Following12061414
LiveBench Instruction Following58.1%—

Long Context GPT-6 Luna leads

Gemma 2 27B: 37.3 (#213), GPT-6 Luna: 43.3 (#95)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Longer Query12311417

Writing & Preference GPT-6 Luna leads

Gemma 2 27B: 44.4 (#220), GPT-6 Luna: 58.4 (#115)

BenchmarkGemma 2 27BGPT-6 Luna
LMArena Text12311392
LMArena Creative Writing12411357
LMArena Multi-Turn12241400
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 29.2 on the Noometry Index.

Which is cheaper, Gemma 2 27B or GPT-6 Luna?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

Is Gemma 2 27B or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 8K.

How many benchmarks do Gemma 2 27B and GPT-6 Luna share?

13 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and GPT-6 Luna has 18.

Related comparisons

Go deeper