Noometry

Model comparison

Gemma 2 9B vs Phi 3 Small 8k Instruct

Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 25.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Gemma 2 9B scores higher in 6 categories and Phi 3 Small 8k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Phi 3 Small 8k Instruct leads 29.1 to 9.7.
  • The biggest single-benchmark swing is LiveBench Language: 25.5% for Gemma 2 9B and 12.9% for Phi 3 Small 8k Instruct.

Side by side

Gemma 2 9BPhi 3 Small 8k Instruct
ProviderGoogleMicrosoft
Noometry Index25.929.3
Released2024-06-242024-04-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3532

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

Category by category

Coding Gemma 2 9B leads

Gemma 2 9B: 29.4 (#304), Phi 3 Small 8k Instruct: 27.9 (#318)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LiveBench Coding22.5%20.3%
LMArena Coding11731101
BigCodeBench Instruct34.7%—
BigCodeBench Complete40.6%—

Reasoning Gemma 2 9B leads

Gemma 2 9B: 15.9 (#309), Phi 3 Small 8k Instruct: 14.8 (#323)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LiveBench Reasoning15.2%15.9%
LMArena Hard Prompts11711100
LiveBench Data Analysis36.4%30.3%
LiveBench28.7%24%
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
Epoch Capabilities Index119.83—
HellaSwag—77%
PIQA83.7%—
WinoGrande—81.5%

Math Phi 3 Small 8k Instruct leads

Gemma 2 9B: 9.9 (#318), Phi 3 Small 8k Instruct: 27.6 (#248)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LiveBench Math19.8%17.6%
LMArena Math11831151
OTIS Mock AIME 2024-20250.6%—
MATH Level 521%—
GSM8K84.9%—

Knowledge Phi 3 Small 8k Instruct leads

Gemma 2 9B: 9.7 (#305), Phi 3 Small 8k Instruct: 29.1 (#240)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LMArena Expert11471067
MMLU72.1%75.7%
GPQA Diamond27.5%—
ARC (AI2) Challenge—90.7%
BoolQ85.7%—
OpenBookQA—88%
TriviaQA—58.1%

Multilingual Gemma 2 9B leads

Gemma 2 9B: 36.6 (#238), Phi 3 Small 8k Instruct: 28.5 (#272)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LMArena Non-English11881058
LMArena Chinese11851061
LMArena French11901135
LMArena German11861080
LMArena Japanese1144966
LMArena Korean1137894
LMArena Russian12001111
LMArena Spanish12001111

Instruction Following Gemma 2 9B leads

Gemma 2 9B: 57.6 (#269), Phi 3 Small 8k Instruct: 51.9 (#292)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LiveBench Instruction Following52.6%47.2%
LMArena Instruction Following11781087

Long Context Gemma 2 9B leads

Gemma 2 9B: 36.3 (#233), Phi 3 Small 8k Instruct: 33.0 (#267)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LMArena Longer Query11971088

Writing & Preference Gemma 2 9B leads

Gemma 2 9B: 32.1 (#281), Phi 3 Small 8k Instruct: 31.1 (#284)

BenchmarkGemma 2 9BPhi 3 Small 8k Instruct
LMArena Text12071110
LMArena Creative Writing12061083
LMArena Multi-Turn11931068
LiveBench Language25.5%12.9%
EQ-Bench Creative Writing841—

Frequently asked questions

Is Gemma 2 9B better than Phi 3 Small 8k Instruct?

Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Phi 3 Small 8k Instruct better for coding?

Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 27.9 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Phi 3 Small 8k Instruct share?

25 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper