Noometry

Model comparison

Gemma 2 9B vs o1-mini

o1-mini is the stronger model overall, scoring 34.0 to 25.9 on the Noometry Index.

Last verified . 28 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

o1-mini OpenAI

34.0

Rank #235 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and o1-mini in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where o1-mini leads 35.4 to 9.9.
  • The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 89.2% for o1-mini.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 9Bo1-mini
ProviderGoogleOpenAI
Noometry Index25.934.0
Released2024-06-242024-09-12
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3539

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

Category by category

Coding o1-mini leads

Gemma 2 9B: 29.4 (#304), o1-mini: 35.5 (#224)

BenchmarkGemma 2 9Bo1-mini
LiveBench Coding22.5%48%
LMArena Coding11731362
Aider Polyglot—32.9%
WeirdML—36.3%
BigCodeBench Instruct34.7%—
BigCodeBench Complete40.6%—
HumanEval+—89%
MBPP+—78.8%

Agentic & Tool Use Not comparable

Gemma 2 9B: —, o1-mini: 24.6 (#118)

BenchmarkGemma 2 9Bo1-mini
Cybench—10%

Reasoning Gemma 2 9B leads

Gemma 2 9B: 15.9 (#309), o1-mini: 8.8 (#346)

BenchmarkGemma 2 9Bo1-mini
LiveBench Reasoning15.2%72.3%
LMArena Hard Prompts11711333
LiveBench Data Analysis36.4%57.9%
Epoch Capabilities Index119.83135.82
LiveBench28.7%57.8%
ARC-AGI-2—0.8%
SimpleBench—18.1%
ARC-AGI-1—14%
PIQA83.7%—

Math o1-mini leads

Gemma 2 9B: 9.9 (#318), o1-mini: 35.4 (#186)

BenchmarkGemma 2 9Bo1-mini
OTIS Mock AIME 2024-20250.6%46.9%
LiveBench Math19.8%62%
LMArena Math11831358
MATH Level 521%89.2%
FrontierMath (Feb 2025 set)—1.7%
GSM8K84.9%—

Knowledge o1-mini leads

Gemma 2 9B: 9.7 (#305), o1-mini: 34.9 (#192)

BenchmarkGemma 2 9Bo1-mini
GPQA Diamond27.5%62.4%
LMArena Expert11471316
Confabulations—18.6%
BoolQ85.7%—
MMLU72.1%—

Multilingual o1-mini leads

Gemma 2 9B: 36.6 (#238), o1-mini: 43.6 (#182)

BenchmarkGemma 2 9Bo1-mini
LMArena Non-English11881289
LMArena Chinese11851314
LMArena French11901293
LMArena German11861278
LMArena Japanese11441245
LMArena Korean11371223
LMArena Russian12001283
LMArena Spanish12001303

Instruction Following o1-mini leads

Gemma 2 9B: 57.6 (#269), o1-mini: 66.7 (#206)

BenchmarkGemma 2 9Bo1-mini
LiveBench Instruction Following52.6%65.4%
LMArena Instruction Following11781304

Long Context o1-mini leads

Gemma 2 9B: 36.3 (#233), o1-mini: 40.1 (#161)

BenchmarkGemma 2 9Bo1-mini
LMArena Longer Query11971320

Writing & Preference o1-mini leads

Gemma 2 9B: 32.1 (#281), o1-mini: 48.4 (#202)

BenchmarkGemma 2 9Bo1-mini
LMArena Text12071317
LMArena Creative Writing12061244
LMArena Multi-Turn11931314
LiveBench Language25.5%40.9%
Short-Story Creative Writing—64.9%
EQ-Bench Creative Writing841—

Frequently asked questions

Is Gemma 2 9B better than o1-mini?

o1-mini is the stronger model overall, scoring 34.0 to 25.9 on the Noometry Index.

Is Gemma 2 9B or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.5 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and o1-mini share?

28 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and o1-mini has 39.

Related comparisons

Go deeper