Noometry

Model comparison

Gemma 2 9B vs o1

o1 is the stronger model overall, scoring 40.9 to 25.9 on the Noometry Index.

Last verified . 28 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

o1 OpenAI

40.9

Rank #143 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where o1 leads 41.5 to 9.7.
  • The biggest single-benchmark swing is LiveBench Reasoning: 15.2% for Gemma 2 9B and 91.6% for o1.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 9Bo1
ProviderGoogleOpenAI
Noometry Index25.940.9
Released2024-06-242024-09-12
WeightsOpenProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$15
Output $ / M tokens—$60
Results tracked3552

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

Category by category

Coding o1 leads

Gemma 2 9B: 29.4 (#304), o1: 46.1 (#70)

BenchmarkGemma 2 9Bo1
LiveBench Coding22.5%69.7%
LMArena Coding11731367
Aider Polyglot—61.7%
WeirdML—47.6%
BigCodeBench Instruct34.7%—
BigCodeBench Complete40.6%—
CadEval—56%
HumanEval+—89%
MBPP+—80.2%

Agentic & Tool Use Not comparable

Gemma 2 9B: —, o1: 24.6 (#117)

BenchmarkGemma 2 9Bo1
Cybench—10%
METR Time Horizons—51.1%

Reasoning o1 leads

Gemma 2 9B: 15.9 (#309), o1: 27.9 (#111)

BenchmarkGemma 2 9Bo1
LiveBench Reasoning15.2%91.6%
LMArena Hard Prompts11711371
LiveBench Data Analysis36.4%65.5%
Epoch Capabilities Index119.83141.91
LiveBench28.7%75.7%
SimpleBench—41.7%
ARC-AGI-1—30.7%
Chess Puzzles—15%
EnigmaEval—5.7%
DTBench—74.7%
LMCA—22.3%
PIQA83.7%—

Math o1 leads

Gemma 2 9B: 9.9 (#318), o1: 36.1 (#175)

BenchmarkGemma 2 9Bo1
OTIS Mock AIME 2024-20250.6%73.3%
LiveBench Math19.8%80.3%
LMArena Math11831388
MATH Level 521%94.7%
FrontierMath (Tiers 1-3)—14.7%
FrontierMath (Feb 2025 set)—9.3%
GSM8K84.9%—

Knowledge o1 leads

Gemma 2 9B: 9.7 (#305), o1: 41.5 (#110)

BenchmarkGemma 2 9Bo1
GPQA Diamond27.5%76.8%
LMArena Expert11471361
Humanity's Last Exam—8%
SimpleQA Verified—41.1%
Confabulations—11.7%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, o1: 34.2 (#93)

BenchmarkGemma 2 9Bo1
LMArena Vision—1168
GeoBench—80%
VPCT—37%
SpatialViz-Bench—41.4%

Multilingual o1 leads

Gemma 2 9B: 36.6 (#238), o1: 48.6 (#142)

BenchmarkGemma 2 9Bo1
LMArena Non-English11881358
LMArena Chinese11851394
LMArena French11901344
LMArena German11861337
LMArena Japanese11441346
LMArena Korean11371396
LMArena Russian12001356
LMArena Spanish12001345

Instruction Following o1 leads

Gemma 2 9B: 57.6 (#269), o1: 74.8 (#86)

BenchmarkGemma 2 9Bo1
LiveBench Instruction Following52.6%81.5%
LMArena Instruction Following11781367

Long Context o1 leads

Gemma 2 9B: 36.3 (#233), o1: 50.3 (#9)

BenchmarkGemma 2 9Bo1
LMArena Longer Query11971378
Fiction.LiveBench—83.3%

Writing & Preference o1 leads

Gemma 2 9B: 32.1 (#281), o1: 55.6 (#144)

BenchmarkGemma 2 9Bo1
LMArena Text12071366
LMArena Creative Writing12061348
LMArena Multi-Turn11931369
LiveBench Language25.5%65.4%
Short-Story Creative Writing—70.2%
EQ-Bench Creative Writing841—

Frequently asked questions

Is Gemma 2 9B better than o1?

o1 is the stronger model overall, scoring 40.9 to 25.9 on the Noometry Index.

Is Gemma 2 9B or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 29.4 in the Noometry coding category.

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

28 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and o1 has 52.

Related comparisons

Go deeper