Noometry

Model comparison

Gemini 1.5 Flash (May 2024) vs Phi-2

Gemini 1.5 Flash (May 2024) has enough public results to be ranked (#246); Phi-2 does not yet, so treat this comparison as directional.

Last verified . 4 shared benchmarks.

Gemini 1.5 Flash (May 2024) Google

33.2

Rank #246 Confirmed

Phi-2 Microsoft

—

Unranked

Summary

  • They share 4 benchmarks with published results for both.
  • Phi-2 has downloadable open weights; the other is API-only.

Side by side

Gemini 1.5 Flash (May 2024)Phi-2
ProviderGoogleMicrosoft
Noometry Index33.2—
Released2024-05-142023-12-12
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4211

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

Category by category

Coding Not comparable

Gemini 1.5 Flash (May 2024): 34.4 (#236), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
HumanEval+75.6%45.1%
MBPP+67.5%54.2%
WeirdML24.9%—
BigCodeBench Instruct43.5%—
LMArena Coding1261—
BigCodeBench Complete55.1%—

Agentic & Tool Use Not comparable

Gemini 1.5 Flash (May 2024): 26.6 (#102), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
BALROG14.6%—

Reasoning Not comparable

Gemini 1.5 Flash (May 2024): 21.7 (#215), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
Epoch Capabilities Index129.36107.94
LMArena Hard Prompts1257—
DTBench53.8%—
Adversarial NLI—42.5%
BIG-Bench Hard—59.4%
ForecastBench53.9—
HellaSwag—53.6%
PIQA87.5%—
WinoGrande—54.7%

Math Not comparable

Gemini 1.5 Flash (May 2024): 22.1 (#281), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
OTIS Mock AIME 2024-202516.3%—
Omni-MATH30.4%—
LMArena Math1269—
MATH Level 561.9%—
FrontierMath (Feb 2025 set)0%—
GSM8K82.4%—

Knowledge Not comparable

Gemini 1.5 Flash (May 2024): 26.2 (#260), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
MMLU77.9%58.4%
GPQA Diamond47.3%—
MMLU-Pro67.8%—
GPQA (HELM)43.7%—
LMArena Expert1233—
ARC (AI2) Challenge—75.9%
BoolQ85.8%—
OpenBookQA—73.6%
TriviaQA—45.2%

Multimodal Not comparable

Gemini 1.5 Flash (May 2024): 36.0 (#81), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
LMArena Vision1141—
Video-MME70.3%—
GeoBench76%—

Multilingual Not comparable

Gemini 1.5 Flash (May 2024): 42.9 (#189), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
LMArena Non-English1278—
LMArena Chinese1295—
LMArena French1258—
LMArena German1262—
LMArena Japanese1252—
LMArena Korean1221—
LMArena Russian1288—
LMArena Spanish1243—

Instruction Following Not comparable

Gemini 1.5 Flash (May 2024): 66.8 (#205), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
IFEval83.1%—
LMArena Instruction Following1258—

Long Context Not comparable

Gemini 1.5 Flash (May 2024): 39.0 (#187), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
LMArena Longer Query1284—

Writing & Preference Not comparable

Gemini 1.5 Flash (May 2024): 48.7 (#196), Phi-2: —

BenchmarkGemini 1.5 Flash (May 2024)Phi-2
LMArena Text1287—
LMArena Creative Writing1285—
WildBench79.2%—
LMArena Multi-Turn1253—

Frequently asked questions

Is Gemini 1.5 Flash (May 2024) better than Phi-2?

Gemini 1.5 Flash (May 2024) has enough public results to be ranked (#246); Phi-2 does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 1.5 Flash (May 2024) and Phi-2 share?

4 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Phi-2 has 11.

Related comparisons

Go deeper