Noometry

Model comparison

Gemini 1.5 Flash 8B vs phi-3-medium 14B

Gemini 1.5 Flash 8B and phi-3-medium 14B score almost the same on the Noometry Index (29.9 vs 29.7), so choose on price, context window or the category you care about most.

Last verified . 1 shared benchmarks.

Gemini 1.5 Flash 8B Google

29.9

Rank #301 Confirmed

phi-3-medium 14B Microsoft

29.7

Rank #306 Reported

Summary

  • They share 1 benchmark with published results for both. Gemini 1.5 Flash 8B scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where phi-3-medium 14B leads 27.3 to 14.2.
  • The biggest single-benchmark swing is GPQA Diamond: 33% for Gemini 1.5 Flash 8B and 27.6% for phi-3-medium 14B.
  • phi-3-medium 14B has downloadable open weights; the other is API-only.

Side by side

Gemini 1.5 Flash 8Bphi-3-medium 14B
ProviderGoogleMicrosoft
Noometry Index29.929.7
Released2024-10-032024-04-23
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2113

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

Category by category

Coding phi-3-medium 14B leads

Gemini 1.5 Flash 8B: 35.5 (#225), phi-3-medium 14B: 36.8 (#201)

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
BigCodeBench Instruct—37.6%
LMArena Coding1218—
BigCodeBench Complete—48.7%

Reasoning Not comparable

Gemini 1.5 Flash 8B: 20.0 (#244), phi-3-medium 14B: —

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
LMArena Hard Prompts1209—
DTBench50%—
Adversarial NLI—55.8%
BIG-Bench Hard—81.4%
Epoch Capabilities Index—121.23
HellaSwag—82.4%
WinoGrande—81.5%

Math phi-3-medium 14B leads

Gemini 1.5 Flash 8B: 14.2 (#302), phi-3-medium 14B: 27.3 (#250)

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
OTIS Mock AIME 2024-20254.6%—
LMArena Math1207—
MATH Level 5—17.6%

Knowledge Gemini 1.5 Flash 8B leads

Gemini 1.5 Flash 8B: 16.0 (#289), phi-3-medium 14B: 9.1 (#306)

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
GPQA Diamond33%27.6%
LMArena Expert1185—
ARC (AI2) Challenge—91.6%
MMLU—78%
OpenBookQA—87.4%
TriviaQA—73.9%

Multimodal Not comparable

Gemini 1.5 Flash 8B: 28.2 (#115), phi-3-medium 14B: —

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
LMArena Vision1044—

Multilingual Not comparable

Gemini 1.5 Flash 8B: 38.5 (#229), phi-3-medium 14B: —

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
LMArena Non-English1215—
LMArena Chinese1231—
LMArena French1234—
LMArena German1206—
LMArena Japanese1150—
LMArena Korean1140—
LMArena Russian1236—
LMArena Spanish1212—

Instruction Following Not comparable

Gemini 1.5 Flash 8B: 62.8 (#236), phi-3-medium 14B: —

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
LMArena Instruction Following1199—

Long Context Not comparable

Gemini 1.5 Flash 8B: 37.0 (#225), phi-3-medium 14B: —

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
LMArena Longer Query1219—

Writing & Preference Not comparable

Gemini 1.5 Flash 8B: 42.8 (#232), phi-3-medium 14B: —

BenchmarkGemini 1.5 Flash 8Bphi-3-medium 14B
LMArena Text1226—
LMArena Creative Writing1218—
LMArena Multi-Turn1185—

Frequently asked questions

Is Gemini 1.5 Flash 8B better than phi-3-medium 14B?

Gemini 1.5 Flash 8B and phi-3-medium 14B score almost the same on the Noometry Index (29.9 vs 29.7), so choose on price, context window or the category you care about most.

Is Gemini 1.5 Flash 8B or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 35.5 in the Noometry coding category.

How many benchmarks do Gemini 1.5 Flash 8B and phi-3-medium 14B share?

1 benchmark has published results for both models. Gemini 1.5 Flash 8B has 21 scored results on Noometry and phi-3-medium 14B has 13.

Related comparisons

Go deeper