Noometry

Model comparison

Gemini 3.5 Flash Lite vs phi-3-medium 14B

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 29.7 on the Noometry Index.

Last verified . 2 shared benchmarks.

Gemini 3.5 Flash Lite Google

41.5

Rank #133 Confirmed

phi-3-medium 14B Microsoft

29.7

Rank #306 Reported

Summary

  • They share 2 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 2 categories and phi-3-medium 14B in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.1 to 9.1.
  • The biggest single-benchmark swing is GPQA Diamond: 83.3% for Gemini 3.5 Flash Lite 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 3.5 Flash Litephi-3-medium 14B
ProviderGoogleMicrosoft
Noometry Index41.529.7
Released2026-07-212024-04-23
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.30—
Output $ / M tokens$2.50—
Results tracked3913

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

Category by category

Coding Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 42.4 (#104), phi-3-medium 14B: 36.8 (#201)

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
LMArena WebDev1440—
SciCode41.3%—
WeirdML39%—
BigCodeBench Instruct—37.6%
LMArena Coding1453—
BigCodeBench Complete—48.7%
ALE-Bench765.27—

Agentic & Tool Use Not comparable

Gemini 3.5 Flash Lite: 25.7 (#107), phi-3-medium 14B: —

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
APEX-Agents29.3%—
GDP.pdf10%—

Reasoning Not comparable

Gemini 3.5 Flash Lite: 27.8 (#114), phi-3-medium 14B: —

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
Epoch Capabilities Index145.13121.23
ARC-AGI-210.3%—
NYT Connections (extended)60.4%—
ARC-AGI-153.5%—
CritPt0%—
Chess Puzzles22%—
LMArena Hard Prompts1441—
Mystery Game Puzzles19%—
DTBench83.5%—
LMCA37.6%—
Adversarial NLI—55.8%
BIG-Bench Hard—81.4%
HellaSwag—82.4%
WinoGrande—81.5%

Math phi-3-medium 14B leads

Gemini 3.5 Flash Lite: 25.9 (#264), phi-3-medium 14B: 27.3 (#250)

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
FrontierMath (Tiers 1-3)26%—
FrontierMath Tier 40%—
OTIS Mock AIME 2024-202571.1%—
ProofBench13%—
LMArena Math1433—
MATH Level 5—17.6%

Knowledge Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 50.1 (#72), phi-3-medium 14B: 9.1 (#306)

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
GPQA Diamond83.3%27.6%
LMArena Expert1435—
ARC (AI2) Challenge—91.6%
MMLU—78%
OpenBookQA—87.4%
TriviaQA—73.9%

Multimodal Not comparable

Gemini 3.5 Flash Lite: 41.1 (#40), phi-3-medium 14B: —

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
LMArena Vision1268—

Multilingual Not comparable

Gemini 3.5 Flash Lite: 53.5 (#63), phi-3-medium 14B: —

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
LMArena Non-English1427—
LMArena Chinese1469—
LMArena French1451—
LMArena German1454—
LMArena Japanese1427—
LMArena Korean1407—
LMArena Russian1443—
LMArena Spanish1442—

Instruction Following Not comparable

Gemini 3.5 Flash Lite: 74.8 (#85), phi-3-medium 14B: —

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
LMArena Instruction Following1420—

Long Context Not comparable

Gemini 3.5 Flash Lite: 43.9 (#84), phi-3-medium 14B: —

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
LMArena Longer Query1435—

Writing & Preference Not comparable

Gemini 3.5 Flash Lite: 64.2 (#57), phi-3-medium 14B: —

BenchmarkGemini 3.5 Flash Litephi-3-medium 14B
LMArena Text1435—
LMArena Creative Writing1420—
EQ-Bench Creative Writing1559—
LMArena Multi-Turn1445—

Frequently asked questions

Is Gemini 3.5 Flash Lite better than phi-3-medium 14B?

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 29.7 on the Noometry Index.

Is Gemini 3.5 Flash Lite or phi-3-medium 14B better for coding?

Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.4 versus 36.8 in the Noometry coding category.

How many benchmarks do Gemini 3.5 Flash Lite and phi-3-medium 14B share?

2 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and phi-3-medium 14B has 13.

Related comparisons

Go deeper