Noometry

Model comparison

Gemma 3 27B vs o1-mini

o1-mini is the stronger model overall, scoring 34.0 to 30.8 on the Noometry Index.

Last verified . 31 shared benchmarks.

Gemma 3 27B Google

30.8

Rank #284 Confirmed

o1-mini OpenAI

34.0

Rank #235 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Gemma 3 27B scores higher in 5 categories and o1-mini in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where o1-mini leads 35.5 to 22.5.
  • The biggest single-benchmark swing is LiveBench Reasoning: 43.8% for Gemma 3 27B and 72.3% for o1-mini.
  • Gemma 3 27B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 27Bo1-mini
ProviderGoogleOpenAI
Noometry Index30.834.0
Released2025-03-112024-09-12
WeightsOpenProprietary
Context window131K—
Max output8K—
Input $ / M tokens$0.08—
Output $ / M tokens$0.16—
Results tracked4339

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

Category by category

Coding o1-mini leads

Gemma 3 27B: 22.5 (#334), o1-mini: 35.5 (#224)

BenchmarkGemma 3 27Bo1-mini
Aider Polyglot4.9%32.9%
LiveBench Coding39.9%48%
LMArena Coding13221362
SciCode21.2%—
WeirdML—36.3%
HumanEval+—89%
MBPP+—78.8%

Agentic & Tool Use Too close to call

Gemma 3 27B: 25.1 (#110), o1-mini: 24.6 (#118)

BenchmarkGemma 3 27Bo1-mini
Berkeley Function Calling Leaderboard29.5%—
Cybench—10%

Reasoning Gemma 3 27B leads

Gemma 3 27B: 16.7 (#301), o1-mini: 8.8 (#346)

BenchmarkGemma 3 27Bo1-mini
LiveBench Reasoning43.8%72.3%
LMArena Hard Prompts13401333
LiveBench Data Analysis51.5%57.9%
Epoch Capabilities Index130.04135.82
LiveBench50%57.8%
ARC-AGI-2—0.8%
SimpleBench—18.1%
Kagi LLM Benchmark40.4%—
ARC-AGI-1—14%
CritPt0%—
Chess Puzzles0%—
DTBench52.5%—
LMCA12.3%—

Math o1-mini leads

Gemma 3 27B: 25.9 (#265), o1-mini: 35.4 (#186)

BenchmarkGemma 3 27Bo1-mini
OTIS Mock AIME 2024-202522.5%46.9%
LiveBench Math55.4%62%
LMArena Math13121358
MATH Level 574%89.2%
FrontierMath (Feb 2025 set)—1.7%

Knowledge o1-mini leads

Gemma 3 27B: 25.5 (#261), o1-mini: 34.9 (#192)

BenchmarkGemma 3 27Bo1-mini
GPQA Diamond47.7%62.4%
Confabulations40.3%18.6%
LMArena Expert13041316
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 3 27B: 32.6 (#100), o1-mini: —

BenchmarkGemma 3 27Bo1-mini
LMArena Vision1164—
GeoBench52%—

Multilingual Gemma 3 27B leads

Gemma 3 27B: 46.9 (#155), o1-mini: 43.6 (#182)

BenchmarkGemma 3 27Bo1-mini
LMArena Non-English13341289
LMArena Chinese13461314
LMArena French13681293
LMArena German13621278
LMArena Japanese12871245
LMArena Korean13081223
LMArena Russian13491283
LMArena Spanish13491303

Instruction Following Gemma 3 27B leads

Gemma 3 27B: 70.6 (#160), o1-mini: 66.7 (#206)

BenchmarkGemma 3 27Bo1-mini
LiveBench Instruction Following74.9%65.4%
LMArena Instruction Following13211304

Long Context o1-mini leads

Gemma 3 27B: 27.6 (#293), o1-mini: 40.1 (#161)

BenchmarkGemma 3 27Bo1-mini
LMArena Longer Query13331320
Fiction.LiveBench33.3%—

Writing & Preference Gemma 3 27B leads

Gemma 3 27B: 52.5 (#168), o1-mini: 48.4 (#202)

BenchmarkGemma 3 27Bo1-mini
LMArena Text13581317
LMArena Creative Writing13461244
Short-Story Creative Writing79.9%64.9%
LMArena Multi-Turn13451314
LiveBench Language34.6%40.9%
EQ-Bench Creative Writing1266—

Frequently asked questions

Is Gemma 3 27B better than o1-mini?

o1-mini is the stronger model overall, scoring 34.0 to 30.8 on the Noometry Index.

Is Gemma 3 27B or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.5 versus 22.5 in the Noometry coding category.

How many benchmarks do Gemma 3 27B and o1-mini share?

31 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and o1-mini has 39.

Related comparisons

Go deeper