Noometry

Model comparison

Gemini 3.6 Flash vs Phi-3.5-mini

Gemini 3.6 Flash has enough public results to be ranked (#33); Phi-3.5-mini does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Gemini 3.6 Flash Google

54.1

Rank #33 Confirmed

Phi-3.5-mini Microsoft

36.9

Unranked Sparse

Summary

  • The widest gap is in coding, where Gemini 3.6 Flash leads 50.0 to 34.6.
  • Phi-3.5-mini has downloadable open weights; the other is API-only.

Side by side

Gemini 3.6 FlashPhi-3.5-mini
ProviderGoogleMicrosoft
Noometry Index54.136.9
Released2026-07-212024-08-16
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked465

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

Category by category

Coding Gemini 3.6 Flash leads

Gemini 3.6 Flash: 50.0 (#48), Phi-3.5-mini: 34.6 (#232)

BenchmarkGemini 3.6 FlashPhi-3.5-mini
DeepSWE46.7%—
FrontierCode34.4%—
LMArena WebDev1538—
SciCode52.7%—
WeirdML56.1%—
BigCodeBench Instruct—32.8%
LMArena Coding1491—
BigCodeBench Complete—38.5%
ALE-Bench715.52—

Agentic & Tool Use Not comparable

Gemini 3.6 Flash: 32.3 (#65), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
APEX-Agents46.9%—
GDP.pdf14%—

Reasoning Not comparable

Gemini 3.6 Flash: 58.8 (#22), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
ARC-AGI-260.4%—
NYT Connections (extended)89%—
ARC-AGI-191.2%—
CritPt10.6%—
Chess Puzzles43%—
LMArena Hard Prompts1485—
Mystery Game Puzzles30%—
DTBench95.5%—
LMCA44.9%—
Epoch Capabilities Index154.25—
PIQA—81%

Math Not comparable

Gemini 3.6 Flash: 57.3 (#40), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
FrontierMath (Tiers 1-3)58.9%—
FrontierMath Tier 422%—
MathArena Final-Answer Competitions70.8%—
OTIS Mock AIME 2024-202594.2%—
ProofBench36%—
LMArena Math1505—
GSM8K—86.2%

Knowledge Not comparable

Gemini 3.6 Flash: 67.8 (#8), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
GPQA Diamond94.1%—
SimpleQA Verified66.2%—
LMArena Expert1488—
BoolQ—78%

Multimodal Not comparable

Gemini 3.6 Flash: 38.5 (#64), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
LMArena Vision1298—
Blueprint-Bench 231.2%—
Furniture Assembly23.3%—
LMArena Document1456—

Multilingual Not comparable

Gemini 3.6 Flash: 56.5 (#19), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
LMArena Non-English1469—
LMArena Chinese1531—
LMArena French1504—
LMArena German1478—
LMArena Japanese1476—
LMArena Korean1431—
LMArena Russian1487—
LMArena Spanish1475—

Instruction Following Not comparable

Gemini 3.6 Flash: 77.0 (#33), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
LMArena Instruction Following1466—

Long Context Not comparable

Gemini 3.6 Flash: 45.1 (#50), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
LMArena Longer Query1474—

Writing & Preference Not comparable

Gemini 3.6 Flash: 68.2 (#27), Phi-3.5-mini: —

BenchmarkGemini 3.6 FlashPhi-3.5-mini
LMArena Text1479—
LMArena Creative Writing1465—
EQ-Bench Creative Writing1604—
LMArena Multi-Turn1481—

Frequently asked questions

Is Gemini 3.6 Flash better than Phi-3.5-mini?

Gemini 3.6 Flash has enough public results to be ranked (#33); Phi-3.5-mini does not yet, so treat this comparison as directional.

Is Gemini 3.6 Flash or Phi-3.5-mini better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 34.6 in the Noometry coding category.

How many benchmarks do Gemini 3.6 Flash and Phi-3.5-mini share?

0 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Phi-3.5-mini has 5.

Related comparisons

Go deeper