Noometry

Model comparison

Gemini 2.0 Flash-Lite vs phi-3-medium 14B

Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 29.7 on the Noometry Index.

Last verified . 0 shared benchmarks.

Gemini 2.0 Flash-Lite Google

37.8

Rank #194 Confirmed

phi-3-medium 14B Microsoft

29.7

Rank #306 Reported

Summary

  • The widest gap is in knowledge, where Gemini 2.0 Flash-Lite leads 35.0 to 9.1.
  • phi-3-medium 14B has downloadable open weights; the other is API-only.

Side by side

Gemini 2.0 Flash-Litephi-3-medium 14B
ProviderGoogleMicrosoft
Noometry Index37.829.7
Released2025-02-052024-04-23
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3213

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

Category by category

Coding Gemini 2.0 Flash-Lite leads

Gemini 2.0 Flash-Lite: 37.9 (#185), phi-3-medium 14B: 36.8 (#201)

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
BigCodeBench Instruct—37.6%
LiveBench Coding47.1%—
LMArena Coding1322—
BigCodeBench Complete—48.7%

Reasoning Not comparable

Gemini 2.0 Flash-Lite: 22.0 (#210), phi-3-medium 14B: —

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
LiveBench Reasoning50.1%—
LMArena Hard Prompts1324—
DTBench52.5%—
LiveBench Data Analysis65.5%—
Adversarial NLI—55.8%
BIG-Bench Hard—81.4%
Epoch Capabilities Index—121.23
ForecastBench57.1—
HellaSwag—82.4%
LiveBench54.3%—
WinoGrande—81.5%

Math Gemini 2.0 Flash-Lite leads

Gemini 2.0 Flash-Lite: 34.1 (#196), phi-3-medium 14B: 27.3 (#250)

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
Omni-MATH37.4%—
LiveBench Math58.1%—
LMArena Math1309—
MATH Level 5—17.6%

Knowledge Gemini 2.0 Flash-Lite leads

Gemini 2.0 Flash-Lite: 35.0 (#189), phi-3-medium 14B: 9.1 (#306)

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
GPQA Diamond—27.6%
MMLU-Pro72%—
GPQA (HELM)50%—
LMArena Expert1305—
ARC (AI2) Challenge—91.6%
MMLU—78%
OpenBookQA—87.4%
TriviaQA—73.9%

Multimodal Not comparable

Gemini 2.0 Flash-Lite: 31.2 (#109), phi-3-medium 14B: —

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
LMArena Vision1100—

Multilingual Not comparable

Gemini 2.0 Flash-Lite: 46.0 (#161), phi-3-medium 14B: —

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
LMArena Non-English1323—
LMArena Chinese1339—
LMArena French1347—
LMArena German1306—
LMArena Japanese1301—
LMArena Korean1325—
LMArena Russian1328—
LMArena Spanish1313—

Instruction Following Not comparable

Gemini 2.0 Flash-Lite: 70.4 (#163), phi-3-medium 14B: —

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
LiveBench Instruction Following78.3%—
IFEval82.4%—
LMArena Instruction Following1305—

Long Context Not comparable

Gemini 2.0 Flash-Lite: 40.1 (#160), phi-3-medium 14B: —

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
LMArena Longer Query1320—

Writing & Preference Not comparable

Gemini 2.0 Flash-Lite: 51.7 (#177), phi-3-medium 14B: —

BenchmarkGemini 2.0 Flash-Litephi-3-medium 14B
LMArena Text1330—
LMArena Creative Writing1319—
WildBench79%—
LMArena Multi-Turn1307—
LiveBench Language34.3%—

Frequently asked questions

Is Gemini 2.0 Flash-Lite better than phi-3-medium 14B?

Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 29.7 on the Noometry Index.

Is Gemini 2.0 Flash-Lite or phi-3-medium 14B better for coding?

Gemini 2.0 Flash-Lite scores higher on coding benchmarks: 37.9 versus 36.8 in the Noometry coding category.

How many benchmarks do Gemini 2.0 Flash-Lite and phi-3-medium 14B share?

0 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and phi-3-medium 14B has 13.

Related comparisons

Go deeper