Noometry

Model comparison

Gemma 2 9B vs GPT-4.1 mini

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 25.9 on the Noometry Index.

Last verified . 23 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Gemma 2 9B scores higher in 2 categories and GPT-4.1 mini in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 mini leads 34.7 to 9.7.
  • The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 87.3% for GPT-4.1 mini.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 9BGPT-4.1 mini
ProviderGoogleOpenAI
Noometry Index25.933.6
Released2024-06-242025-04-14
WeightsOpenProprietary
Context window—1.05M
Max output—33K
Input $ / M tokens—$0.40
Output $ / M tokens—$1.60
Results tracked3547

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

Category by category

Coding GPT-4.1 mini leads

Gemma 2 9B: 29.4 (#304), GPT-4.1 mini: 30.6 (#293)

BenchmarkGemma 2 9BGPT-4.1 mini
BigCodeBench Instruct34.7%48.9%
LMArena Coding11731367
SWE-bench Verified (bash only)—23.9%
Aider Polyglot—32.4%
SciCode—40.4%
WeirdML—37.6%
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
CadEval—16%

Agentic & Tool Use Not comparable

Gemma 2 9B: —, GPT-4.1 mini: 33.3 (#55)

BenchmarkGemma 2 9BGPT-4.1 mini
Berkeley Function Calling Leaderboard—50.5%

Reasoning Gemma 2 9B leads

Gemma 2 9B: 15.9 (#309), GPT-4.1 mini: 10.8 (#340)

BenchmarkGemma 2 9BGPT-4.1 mini
LMArena Hard Prompts11711349
Epoch Capabilities Index119.83135.01
ARC-AGI-2—0%
Kagi LLM Benchmark—48.6%
ARC-AGI-1—3.5%
CritPt—0%
Chess Puzzles—7%
LiveBench Reasoning15.2%—
Mystery Game Puzzles—7%
DTBench—68.8%
LiveBench Data Analysis36.4%—
LMCA—21.1%
LiveBench28.7%—
PIQA83.7%—

Math GPT-4.1 mini leads

Gemma 2 9B: 9.9 (#318), GPT-4.1 mini: 24.1 (#270)

BenchmarkGemma 2 9BGPT-4.1 mini
OTIS Mock AIME 2024-20250.6%44.7%
LMArena Math11831343
MATH Level 521%87.3%
FrontierMath (Tiers 1-3)—6.7%
Omni-MATH—49.1%
LiveBench Math19.8%—
FrontierMath (Feb 2025 set)—4.5%
GSM8K84.9%—

Knowledge GPT-4.1 mini leads

Gemma 2 9B: 9.7 (#305), GPT-4.1 mini: 34.7 (#194)

BenchmarkGemma 2 9BGPT-4.1 mini
GPQA Diamond27.5%65.8%
LMArena Expert11471338
SimpleQA Verified—12.7%
MMLU-Pro—78.3%
GPQA (HELM)—61.4%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, GPT-4.1 mini: 35.8 (#82)

BenchmarkGemma 2 9BGPT-4.1 mini
LMArena Vision—1181

Multilingual GPT-4.1 mini leads

Gemma 2 9B: 36.6 (#238), GPT-4.1 mini: 45.7 (#166)

BenchmarkGemma 2 9BGPT-4.1 mini
LMArena Non-English11881318
LMArena Chinese11851329
LMArena French11901358
LMArena German11861351
LMArena Japanese11441290
LMArena Korean11371298
LMArena Russian12001324
LMArena Spanish12001319

Instruction Following GPT-4.1 mini leads

Gemma 2 9B: 57.6 (#269), GPT-4.1 mini: 73.7 (#118)

BenchmarkGemma 2 9BGPT-4.1 mini
LMArena Instruction Following11781333
LiveBench Instruction Following52.6%—
IFEval—90.4%

Long Context Gemma 2 9B leads

Gemma 2 9B: 36.3 (#233), GPT-4.1 mini: 31.8 (#275)

BenchmarkGemma 2 9BGPT-4.1 mini
LMArena Longer Query11971344
Fiction.LiveBench—44.4%

Writing & Preference GPT-4.1 mini leads

Gemma 2 9B: 32.1 (#281), GPT-4.1 mini: 48.6 (#199)

BenchmarkGemma 2 9BGPT-4.1 mini
LMArena Text12071340
LMArena Creative Writing12061300
EQ-Bench Creative Writing8411147
LMArena Multi-Turn11931354
WildBench—83.8%
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than GPT-4.1 mini?

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 25.9 on the Noometry Index.

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

GPT-4.1 mini scores higher on coding benchmarks: 30.6 versus 29.4 in the Noometry coding category.

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

23 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-4.1 mini has 47.

Related comparisons

Go deeper