Noometry

Model comparison

Gemma 7B vs GPT-5.2

GPT-5.2 is the stronger model overall, scoring 54.1 to 30.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

Gemma 7B Google

30.0

Rank #299 Confirmed

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and GPT-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.2 leads 66.8 to 27.1.
  • Gemma 7B has downloadable open weights; the other is API-only.

Side by side

Gemma 7BGPT-5.2
ProviderGoogleOpenAI
Noometry Index30.054.1
Released2024-02-212025-12-11
WeightsOpenProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$1.75
Output $ / M tokens—$14
Results tracked2767

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

Category by category

Coding GPT-5.2 leads

Gemma 7B: 30.5 (#294), GPT-5.2: 51.6 (#37)

BenchmarkGemma 7BGPT-5.2
LMArena Coding10481447
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—72.8%
LMArena WebDev—1416
SWE-bench Multilingual—66.7%
GSO—27.4%
WeirdML—72.2%
ALE-Bench—1,294
AlgoTune—2.05
HumanEval+28.7%—
MBPP+43.4%—

Agentic & Tool Use Not comparable

Gemma 7B: —, GPT-5.2: 40.2 (#24)

BenchmarkGemma 7BGPT-5.2
Terminal-Bench—64.9%
Berkeley Function Calling Leaderboard—55.9%
GDPval—49.7%
Remote Labor Index—2.5%
τ²-bench Airline—83%
τ²-bench Banking—32.2%
τ²-bench Retail—81.6%
τ²-bench Telecom—89.7%
DeepResearch Bench—41.1%
LMArena Search—1207
METR Time Horizons—75.3%
Vending-Bench 2—3,591

Reasoning GPT-5.2 leads

Gemma 7B: 19.9 (#249), GPT-5.2: 50.2 (#35)

BenchmarkGemma 7BGPT-5.2
LMArena Hard Prompts10421445
Epoch Capabilities Index111.99153.45
ARC-AGI-2—52.9%
SimpleBench—45.8%
Kagi LLM Benchmark—73.3%
NYT Connections (extended)—83.6%
ARC-AGI-1—86.2%
Chess Puzzles—49%
EnigmaEval—10.4%
EBR-Bench—23%
Mystery Game Puzzles—23%
DTBench—90.9%
LMCA—43.9%
Adversarial NLI48.7%—
BIG-Bench Hard55.1%—
ForecastBench—60.1
HellaSwag82.2%—
PIQA81.2%—
WinoGrande79%—

Math GPT-5.2 leads

Gemma 7B: 31.2 (#228), GPT-5.2: 60.0 (#38)

BenchmarkGemma 7BGPT-5.2
LMArena Math10661440
FrontierMath (Tiers 1-3)—67.4%
FrontierMath Tier 4—31.7%
MathArena Final-Answer Competitions—72%
OTIS Mock AIME 2024-2025—96.1%
ProofBench—15%
FrontierMath (Feb 2025 set)—40.7%
FrontierMath Tier 4 (v1)—18.8%
GSM8K46.4%—

Knowledge GPT-5.2 leads

Gemma 7B: 27.3 (#252), GPT-5.2: 59.3 (#32)

BenchmarkGemma 7BGPT-5.2
LMArena Expert10011445
GPQA Diamond—91.4%
Humanity's Last Exam—27.8%
SimpleQA Verified—37.1%
Vectara Hallucination Rate—8.4%
ARC (AI2) Challenge78.3%—
BoolQ83.2%—
MMLU66.1%—
OpenBookQA78.6%—
TriviaQA72.3%—

Multimodal Not comparable

Gemma 7B: —, GPT-5.2: 51.3 (#7)

BenchmarkGemma 7BGPT-5.2
LMArena Vision—1268
VPCT—84%
Furniture Assembly—38.3%
LMArena Document—1405

Multilingual GPT-5.2 leads

Gemma 7B: 25.1 (#287), GPT-5.2: 53.4 (#67)

BenchmarkGemma 7BGPT-5.2
LMArena Non-English9991425
LMArena Chinese10351460
LMArena French10251455
LMArena Russian9931440
LMArena German—1448
LMArena Japanese—1420
LMArena Korean—1392
LMArena Spanish—1433

Instruction Following GPT-5.2 leads

Gemma 7B: 51.5 (#295), GPT-5.2: 74.7 (#89)

BenchmarkGemma 7BGPT-5.2
LMArena Instruction Following10171417

Long Context GPT-5.2 leads

Gemma 7B: 31.1 (#282), GPT-5.2: 44.0 (#78)

BenchmarkGemma 7BGPT-5.2
LMArena Longer Query10221428
CL-bench—18.2%

Writing & Preference GPT-5.2 leads

Gemma 7B: 27.1 (#302), GPT-5.2: 66.8 (#32)

BenchmarkGemma 7BGPT-5.2
LMArena Text10561439
LMArena Creative Writing10241401
LMArena Multi-Turn9631458
EQ-Bench Creative Writing—1703

Frequently asked questions

Is Gemma 7B better than GPT-5.2?

GPT-5.2 is the stronger model overall, scoring 54.1 to 30.0 on the Noometry Index.

Is Gemma 7B or GPT-5.2 better for coding?

GPT-5.2 scores higher on coding benchmarks: 51.6 versus 30.5 in the Noometry coding category.

How many benchmarks do Gemma 7B and GPT-5.2 share?

14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and GPT-5.2 has 67.

Related comparisons

Go deeper