Noometry

Model comparison

Gemma 2 9B vs GPT-4.1

GPT-4.1 is the stronger model overall, scoring 35.9 to 25.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and GPT-4.1 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 leads 37.1 to 9.7.
  • The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 83% for GPT-4.1.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 9BGPT-4.1
ProviderGoogleOpenAI
Noometry Index25.935.9
Released2024-06-242025-04-14
WeightsOpenProprietary
Context window—1.05M
Max output—33K
Input $ / M tokens—$2
Output $ / M tokens—$8
Results tracked3552

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

Category by category

Coding GPT-4.1 leads

Gemma 2 9B: 29.4 (#304), GPT-4.1: 34.4 (#238)

BenchmarkGemma 2 9BGPT-4.1
LMArena Coding11731391
SWE-bench Verified—48.5%
SWE-bench Verified (bash only)—39.6%
Aider Polyglot—52.4%
WeirdML—39%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
CadEval—42%
ALE-Bench—558.1

Agentic & Tool Use Not comparable

Gemma 2 9B: —, GPT-4.1: 34.7 (#43)

BenchmarkGemma 2 9BGPT-4.1
Berkeley Function Calling Leaderboard—54%

Reasoning Gemma 2 9B leads

Gemma 2 9B: 15.9 (#309), GPT-4.1: 11.7 (#339)

BenchmarkGemma 2 9BGPT-4.1
LMArena Hard Prompts11711384
Epoch Capabilities Index119.83136.78
ARC-AGI-2—0.4%
SimpleBench—27%
Kagi LLM Benchmark—52.3%
ARC-AGI-1—5.5%
Chess Puzzles—6%
EnigmaEval—2.2%
LiveBench Reasoning15.2%—
DTBench—68.3%
LiveBench Data Analysis36.4%—
LMCA—25.6%
ForecastBench—61.5
LiveBench28.7%—
PIQA83.7%—

Math GPT-4.1 leads

Gemma 2 9B: 9.9 (#318), GPT-4.1: 22.3 (#280)

BenchmarkGemma 2 9BGPT-4.1
OTIS Mock AIME 2024-20250.6%38.3%
LMArena Math11831370
MATH Level 521%83%
FrontierMath (Tiers 1-3)—6%
Omni-MATH—47.1%
LiveBench Math19.8%—
FrontierMath (Feb 2025 set)—5.5%
FrontierMath Tier 4 (v1)—0%
GSM8K84.9%—

Knowledge GPT-4.1 leads

Gemma 2 9B: 9.7 (#305), GPT-4.1: 37.1 (#160)

BenchmarkGemma 2 9BGPT-4.1
GPQA Diamond27.5%66.9%
LMArena Expert11471364
Humanity's Last Exam—5.4%
SimpleQA Verified—31.1%
MMLU-Pro—81.1%
Vectara Hallucination Rate—5.6%
GPQA (HELM)—65.9%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, GPT-4.1: 38.2 (#67)

BenchmarkGemma 2 9BGPT-4.1
LMArena Vision—1211
GeoBench—72%

Multilingual GPT-4.1 leads

Gemma 2 9B: 36.6 (#238), GPT-4.1: 49.4 (#133)

BenchmarkGemma 2 9BGPT-4.1
LMArena Non-English11881370
LMArena Chinese11851382
LMArena French11901382
LMArena German11861381
LMArena Japanese11441319
LMArena Korean11371339
LMArena Russian12001377
LMArena Spanish12001376

Instruction Following GPT-4.1 leads

Gemma 2 9B: 57.6 (#269), GPT-4.1: 71.3 (#153)

BenchmarkGemma 2 9BGPT-4.1
LMArena Instruction Following11781367
LiveBench Instruction Following52.6%—
IFEval—83.8%

Long Context GPT-4.1 leads

Gemma 2 9B: 36.3 (#233), GPT-4.1: 40.0 (#163)

BenchmarkGemma 2 9BGPT-4.1
LMArena Longer Query11971385
Fiction.LiveBench—63.9%

Writing & Preference GPT-4.1 leads

Gemma 2 9B: 32.1 (#281), GPT-4.1: 57.6 (#125)

BenchmarkGemma 2 9BGPT-4.1
LMArena Text12071383
LMArena Creative Writing12061363
EQ-Bench Creative Writing8411420
LMArena Multi-Turn11931398
WildBench—85.4%
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than GPT-4.1?

GPT-4.1 is the stronger model overall, scoring 35.9 to 25.9 on the Noometry Index.

Is Gemma 2 9B or GPT-4.1 better for coding?

GPT-4.1 scores higher on coding benchmarks: 34.4 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and GPT-4.1 share?

22 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-4.1 has 52.

Related comparisons

Go deeper