Model comparison

Gemini 3.5 Flash Lite vs Yi-Lightning

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 37.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemini 3.5 Flash Lite Google

41.5

Rank #133 Confirmed

Yi-Lightning 01.AI

37.1

Rank #209 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 7 categories and Yi-Lightning in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Gemini 3.5 Flash Lite leads 42.4 to 27.4.

Side by side

Gemini 3.5 Flash Lite and Yi-Lightning specifications
Gemini 3.5 Flash LiteYi-Lightning
ProviderGoogle01.AI
Noometry Index41.537.1
Released2026-07-212024-12-02
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$0.30—
Output $ / M tokens$2.50—
Results tracked3918

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

Category by category

Coding Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 42.4 (#104), Yi-Lightning: 27.4 (#320)

Coding benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Coding14531312
Aider Polyglot—12.9%
LMArena WebDev1440—
SciCode41.3%—
WeirdML39%—
ALE-Bench765.27—

Agentic & Tool Use Not comparable

Gemini 3.5 Flash Lite: 25.7 (#107), Yi-Lightning: —

Agentic & Tool Use benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
APEX-Agents29.3%—
GDP.pdf10%—

Reasoning Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 27.8 (#114), Yi-Lightning: 25.9 (#139)

Reasoning benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Hard Prompts14411302
ARC-AGI-210.3%—
NYT Connections (extended)60.4%—
ARC-AGI-153.5%—
CritPt0%—
Chess Puzzles22%—
Mystery Game Puzzles19%—
DTBench83.5%—
LMCA37.6%—
Epoch Capabilities Index145.13—

Math Yi-Lightning leads

Gemini 3.5 Flash Lite: 25.9 (#264), Yi-Lightning: 36.2 (#172)

Math benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Math14331300
FrontierMath (Tiers 1-3)26%—
FrontierMath Tier 40%—
OTIS Mock AIME 2024-202571.1%—
ProofBench13%—

Knowledge Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 50.1 (#72), Yi-Lightning: 35.4 (#185)

Knowledge benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Expert14351286
GPQA Diamond83.3%—

Multimodal Not comparable

Gemini 3.5 Flash Lite: 41.1 (#40), Yi-Lightning: —

Multimodal benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Vision1268—

Multilingual Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 53.5 (#63), Yi-Lightning: 42.2 (#196)

Multilingual benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Non-English14271269
LMArena Chinese14691320
LMArena French14511305
LMArena German14541267
LMArena Japanese14271228
LMArena Korean14071192
LMArena Russian14431255
LMArena Spanish14421315

Instruction Following Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 74.8 (#85), Yi-Lightning: 67.4 (#196)

Instruction Following benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Instruction Following14201278

Long Context Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 43.9 (#84), Yi-Lightning: 39.4 (#181)

Long Context benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Longer Query14351297

Writing & Preference Gemini 3.5 Flash Lite leads

Gemini 3.5 Flash Lite: 64.2 (#57), Yi-Lightning: 50.2 (#184)

Writing & Preference benchmarks
BenchmarkGemini 3.5 Flash LiteYi-Lightning
LMArena Text14351302
LMArena Creative Writing14201280
LMArena Multi-Turn14451311
EQ-Bench Creative Writing1559—

Frequently asked questions

Is Gemini 3.5 Flash Lite better than Yi-Lightning?

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 37.1 on the Noometry Index.

Is Gemini 3.5 Flash Lite or Yi-Lightning better for coding?

Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.4 versus 27.4 in the Noometry coding category.

How many benchmarks do Gemini 3.5 Flash Lite and Yi-Lightning share?

17 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Yi-Lightning has 18.

Related comparisons

Go deeper