Noometry

Model comparison

Gemma 2B vs GPT-5.4

GPT-5.4 is the stronger model overall, scoring 59.4 to 29.6 on the Noometry Index.

Last verified . 12 shared benchmarks.

Gemma 2B Google

29.6

Rank #307 Confirmed

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and GPT-5.4 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.4 leads 71.9 to 24.0.
  • Gemma 2B has downloadable open weights; the other is API-only.

Side by side

Gemma 2BGPT-5.4
ProviderGoogleOpenAI
Noometry Index29.659.4
Released2024-02-212026-03-05
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2.50
Output $ / M tokens—$15
Results tracked2368

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

Category by category

Coding GPT-5.4 leads

Gemma 2B: 29.4 (#305), GPT-5.4: 52.6 (#33)

BenchmarkGemma 2BGPT-5.4
LMArena Coding10101497
SWE-bench Verified—76.9%
DeepSWE—51.8%
LMArena WebDev—1465
SciCode—56.6%
GSO—31.4%
WeirdML—77.7%
MirrorCode—15.6%
ALE-Bench—1,607
AlgoTune—1.85
HumanEval+20.7%—
MBPP+34.1%—

Agentic & Tool Use Not comparable

Gemma 2B: —, GPT-5.4: 46.5 (#13)

BenchmarkGemma 2BGPT-5.4
Terminal-Bench—81.8%
APEX-Agents—52.4%
τ²-bench Banking—39.4%
DeepResearch Bench—35.1%
PostTrainBench—19%
GBAEval—45.1%
LMArena Search—1197
METR Time Horizons—74.3%
Vending-Bench 2—6,144

Reasoning GPT-5.4 leads

Gemma 2B: 18.8 (#275), GPT-5.4: 61.8 (#19)

BenchmarkGemma 2BGPT-5.4
LMArena Hard Prompts9891485
Epoch Capabilities Index94.2156.81
ARC-AGI-2—74%
Kagi LLM Benchmark—63.8%
NYT Connections (extended)—91.3%
ARC-AGI-1—93.7%
CritPt—23.4%
Chess Puzzles—44%
EnigmaEval—16%
Thematic Generalization—80%
EBR-Bench—25.4%
Mystery Game Puzzles—37%
DTBench—94.4%
LMCA—52%
BIG-Bench Hard35.2%—
ForecastBench—59.5
HellaSwag71.4%—
PIQA77.3%—
WinoGrande65.4%—

Math GPT-5.4 leads

Gemma 2B: 30.0 (#239), GPT-5.4: 73.5 (#19)

BenchmarkGemma 2BGPT-5.4
LMArena Math10091488
FrontierMath (Tiers 1-3)—78.6%
FrontierMath Tier 4—49%
MathArena Final-Answer Competitions—83.1%
OTIS Mock AIME 2024-2025—97.8%
ProofBench—56%
FrontierMath (Feb 2025 set)—47.6%
FrontierMath Tier 4 (v1)—27.1%
GSM8K17.7%—

Knowledge Not comparable

Gemma 2B: —, GPT-5.4: 65.3 (#14)

BenchmarkGemma 2BGPT-5.4
GPQA Diamond—93.3%
Humanity's Last Exam—36.2%
SimpleQA Verified—45.1%
Vectara Hallucination Rate—7%
LMArena Expert—1507
ARC (AI2) Challenge42.1%—
BoolQ69.4%—
MMLU42.3%—
TriviaQA53.2%—

Multimodal Not comparable

Gemma 2B: —, GPT-5.4: 43.7 (#20)

BenchmarkGemma 2BGPT-5.4
LMArena Vision—1303
Blueprint-Bench 2—27.1%
Furniture Assembly—37.5%
LMArena Document—1471

Multilingual GPT-5.4 leads

Gemma 2B: 23.0 (#294), GPT-5.4: 56.2 (#23)

BenchmarkGemma 2BGPT-5.4
LMArena Non-English9581465
LMArena Chinese9861519
LMArena Russian9371480
LMArena French—1493
LMArena German—1472
LMArena Japanese—1485
LMArena Korean—1448
LMArena Spanish—1454

Instruction Following GPT-5.4 leads

Gemma 2B: 48.5 (#302), GPT-5.4: 77.1 (#27)

BenchmarkGemma 2BGPT-5.4
LMArena Instruction Following9701469

Long Context GPT-5.4 leads

Gemma 2B: 29.9 (#291), GPT-5.4: 50.3 (#8)

BenchmarkGemma 2BGPT-5.4
LMArena Longer Query9811473
CL-bench—27.9%
CL-bench Life—21.7%

Writing & Preference GPT-5.4 leads

Gemma 2B: 24.0 (#308), GPT-5.4: 71.9 (#17)

BenchmarkGemma 2BGPT-5.4
LMArena Text10021469
LMArena Creative Writing9871439
LMArena Multi-Turn9451482
EQ-Bench Creative Writing—1840
EQ-Bench 4—1272

Frequently asked questions

Is Gemma 2B better than GPT-5.4?

GPT-5.4 is the stronger model overall, scoring 59.4 to 29.6 on the Noometry Index.

Is Gemma 2B or GPT-5.4 better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.6 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2B and GPT-5.4 share?

12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and GPT-5.4 has 68.

Related comparisons

Go deeper