Noometry

Model comparison

Gemini 3.7 Flash vs Phi-3.5-mini

Gemini 3.7 Flash has enough public results to be ranked (#14); Phi-3.5-mini does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #14 Confirmed

Phi-3.5-mini Microsoft

36.9

Unranked Sparse

Summary

  • The widest gap is in coding, where Gemini 3.7 Flash leads 56.2 to 34.6.
  • Phi-3.5-mini has downloadable open weights; the other is API-only.

Side by side

Gemini 3.7 FlashPhi-3.5-mini
ProviderGoogleMicrosoft
Noometry Index59.836.9
Released2026-08-132024-08-16
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked445

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

Category by category

Coding Gemini 3.7 Flash leads

Gemini 3.7 Flash: 56.2 (#22), Phi-3.5-mini: 34.6 (#232)

BenchmarkGemini 3.7 FlashPhi-3.5-mini
DeepSWE65.5%—
FrontierCode43.6%—
LMArena WebDev1592—
FrontierSWE20.3%—
SciCode59.8%—
BigCodeBench Instruct—32.8%
LMArena Coding1497—
BigCodeBench Complete—38.5%
ALE-Bench904.3—

Agentic & Tool Use Not comparable

Gemini 3.7 Flash: 42.1 (#19), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
APEX-Agents67.8%—
Remote Labor Index5%—
GDP.pdf23.8%—

Reasoning Not comparable

Gemini 3.7 Flash: 70.0 (#15), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
ARC-AGI-284.6%—
NYT Connections (extended)94%—
ARC-AGI-195.5%—
CritPt14.3%—
Chess Puzzles47%—
LMArena Hard Prompts1494—
Mystery Game Puzzles37%—
DTBench96.8%—
LMCA50.4%—
Epoch Capabilities Index157.27—
PIQA—81%

Math Not comparable

Gemini 3.7 Flash: 69.6 (#23), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
FrontierMath (Tiers 1-3)71.6%—
FrontierMath Tier 436.6%—
OTIS Mock AIME 2024-202597.2%—
ProofBench58%—
LMArena Math1507—
GSM8K—86.2%

Knowledge Not comparable

Gemini 3.7 Flash: 69.7 (#5), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
GPQA Diamond94.8%—
SimpleQA Verified69.2%—
LMArena Expert1508—
BoolQ—78%

Multimodal Not comparable

Gemini 3.7 Flash: 37.3 (#73), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
LMArena Vision1316—
Furniture Assembly26.7%—

Multilingual Not comparable

Gemini 3.7 Flash: 57.6 (#7), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
LMArena Non-English1484—
LMArena Chinese1548—
LMArena French1505—
LMArena German1498—
LMArena Japanese1512—
LMArena Korean1483—
LMArena Russian1516—
LMArena Spanish1503—

Instruction Following Not comparable

Gemini 3.7 Flash: 77.7 (#15), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
LMArena Instruction Following1483—

Long Context Not comparable

Gemini 3.7 Flash: 45.7 (#30), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
LMArena Longer Query1492—

Writing & Preference Not comparable

Gemini 3.7 Flash: 71.2 (#20), Phi-3.5-mini: —

BenchmarkGemini 3.7 FlashPhi-3.5-mini
LMArena Text1486—
LMArena Creative Writing1490—
EQ-Bench Creative Writing1723—
LMArena Multi-Turn1489—

Frequently asked questions

Is Gemini 3.7 Flash better than Phi-3.5-mini?

Gemini 3.7 Flash has enough public results to be ranked (#14); Phi-3.5-mini does not yet, so treat this comparison as directional.

Is Gemini 3.7 Flash or Phi-3.5-mini better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 34.6 in the Noometry coding category.

How many benchmarks do Gemini 3.7 Flash and Phi-3.5-mini share?

0 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Phi-3.5-mini has 5.

Related comparisons

Go deeper