Noometry

Model comparison

Gemini 3.5 Flash vs Phi-2

Gemini 3.5 Flash has enough public results to be ranked (#32); Phi-2 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Gemini 3.5 Flash Google

54.2

Rank #32 Confirmed

Phi-2 Microsoft

—

Unranked

Summary

  • They share 1 benchmark with published results for both.
  • Phi-2 has downloadable open weights; the other is API-only.

Side by side

Gemini 3.5 FlashPhi-2
ProviderGoogleMicrosoft
Noometry Index54.2—
Released2026-05-192023-12-12
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$1.50—
Output $ / M tokens$9—
Results tracked5411

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

Category by category

Coding Not comparable

Gemini 3.5 Flash: 49.4 (#49), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
SWE-bench Verified79.3%—
DeepSWE37.4%—
LMArena WebDev1499—
SciCode53.1%—
WeirdML62.6%—
LMArena Coding1492—
ALE-Bench911.02—
HumanEval+—45.1%
MBPP+—54.2%

Agentic & Tool Use Not comparable

Gemini 3.5 Flash: 24.7 (#114), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
APEX-Agents27.5%—
GBAEval6.7%—
GDP.pdf14%—
Vending-Bench 25,396—

Reasoning Not comparable

Gemini 3.5 Flash: 62.8 (#18), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
Epoch Capabilities Index154.46107.94
ARC-AGI-272.1%—
SimpleBench76.7%—
NYT Connections (extended)92.6%—
ARC-AGI-192.5%—
CritPt13.1%—
Chess Puzzles50%—
EnigmaEval25.4%—
EBR-Bench4.8%—
LMArena Hard Prompts1488—
Mystery Game Puzzles32%—
DTBench94.7%—
LMCA47.1%—
Surface Evolver Bench58.1%—
Adversarial NLI—42.5%
BIG-Bench Hard—59.4%
ForecastBench59—
HellaSwag—53.6%
WinoGrande—54.7%

Math Not comparable

Gemini 3.5 Flash: 60.7 (#36), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
FrontierMath (Tiers 1-3)62.8%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions76.3%—
OTIS Mock AIME 2024-202595.6%—
ProofBench31%—
LMArena Math1504—
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Not comparable

Gemini 3.5 Flash: 66.3 (#11), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
GPQA Diamond92.8%—
SimpleQA Verified66.2%—
LMArena Expert1495—
ARC (AI2) Challenge—75.9%
MMLU—58.4%
OpenBookQA—73.6%
TriviaQA—45.2%

Multimodal Not comparable

Gemini 3.5 Flash: 45.7 (#15), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
LMArena Vision1310—
Blueprint-Bench 233.6%—
LMArena Document1463—

Multilingual Not comparable

Gemini 3.5 Flash: 57.0 (#13), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
LMArena Non-English1476—
LMArena Chinese1526—
LMArena French1490—
LMArena German1492—
LMArena Japanese1486—
LMArena Korean1451—
LMArena Russian1493—
LMArena Spanish1480—

Instruction Following Not comparable

Gemini 3.5 Flash: 77.0 (#30), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
LMArena Instruction Following1467—

Long Context Not comparable

Gemini 3.5 Flash: 45.4 (#38), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
LMArena Longer Query1482—

Writing & Preference Not comparable

Gemini 3.5 Flash: 65.5 (#47), Phi-2: —

BenchmarkGemini 3.5 FlashPhi-2
LMArena Text1482—
LMArena Creative Writing1470—
EQ-Bench 41087—
LMArena Multi-Turn1481—

Frequently asked questions

Is Gemini 3.5 Flash better than Phi-2?

Gemini 3.5 Flash has enough public results to be ranked (#32); Phi-2 does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 3.5 Flash and Phi-2 share?

1 benchmark has published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Phi-2 has 11.

Related comparisons

Go deeper