Model comparison

ERNIE 5.1 vs Gemini 3.5 Flash Lite

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 41.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

ERNIE 5.1 Baidu

43.1

Rank #87 Confirmed

Gemini 3.5 Flash Lite Google

41.8

Rank #113 Confirmed

Summary

  • They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 6 categories and Gemini 3.5 Flash Lite in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where ERNIE 5.1 leads 37.5 to 25.7.
  • The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 60.4% for Gemini 3.5 Flash Lite.

Side by side

ERNIE 5.1 and Gemini 3.5 Flash Lite specifications
ERNIE 5.1Gemini 3.5 Flash Lite
ProviderBaiduGoogle
Noometry Index43.141.8
Released—2026-07-21
WeightsProprietaryProprietary
Context window—1.05M
Max output—66K
Input $ / M tokens—$0.30
Output $ / M tokens—$2.50
Results tracked1938

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

Category by category

Coding ERNIE 5.1 leads

ERNIE 5.1: 43.4 (#78), Gemini 3.5 Flash Lite: 42.1 (#96)

Coding benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Coding14881455
LMArena WebDev—1440
SciCode—41.3%
WeirdML—39%
ALE-Bench—765.27

Agentic & Tool Use Not comparable

ERNIE 5.1: —, Gemini 3.5 Flash Lite: 28.6 (#82)

Agentic & Tool Use benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
GDP.pdf—10%
LMArena Search1227—

Reasoning Gemini 3.5 Flash Lite leads

ERNIE 5.1: 20.9 (#209), Gemini 3.5 Flash Lite: 27.8 (#95)

Reasoning benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
NYT Connections (extended)23.4%60.4%
LMArena Hard Prompts14811441
ARC-AGI-2—10.3%
ARC-AGI-1—53.5%
CritPt—0%
Chess Puzzles—22%
Mystery Game Puzzles—19%
DTBench—83.5%
LMCA—37.6%
Epoch Capabilities Index—145.12

Math ERNIE 5.1 leads

ERNIE 5.1: 37.5 (#96), Gemini 3.5 Flash Lite: 25.7 (#245)

Math benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Math14811431
FrontierMath (Tiers 1-3)—26%
FrontierMath Tier 4—0%
OTIS Mock AIME 2024-2025—71.1%
ProofBench—13%

Knowledge Gemini 3.5 Flash Lite leads

ERNIE 5.1: 41.2 (#103), Gemini 3.5 Flash Lite: 50.0 (#66)

Knowledge benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Expert14911430
GPQA Diamond—83.3%

Multimodal Not comparable

ERNIE 5.1: —, Gemini 3.5 Flash Lite: 40.3 (#38)

Multimodal benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Vision—1266

Multilingual ERNIE 5.1 leads

ERNIE 5.1: 55.7 (#28), Gemini 3.5 Flash Lite: 53.8 (#59)

Multilingual benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Non-English14551428
LMArena Chinese15071467
LMArena French14861452
LMArena German14701454
LMArena Japanese14221428
LMArena Korean14281406
LMArena Russian14591443
LMArena Spanish14721440

Instruction Following ERNIE 5.1 leads

ERNIE 5.1: 76.9 (#35), Gemini 3.5 Flash Lite: 75.0 (#77)

Instruction Following benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Instruction Following14601420

Long Context Too close to call

ERNIE 5.1: 44.7 (#56), Gemini 3.5 Flash Lite: 43.8 (#80)

Long Context benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Longer Query14621435

Writing & Preference Too close to call

ERNIE 5.1: 65.3 (#50), Gemini 3.5 Flash Lite: 64.4 (#55)

Writing & Preference benchmarks
BenchmarkERNIE 5.1Gemini 3.5 Flash Lite
LMArena Text14681436
LMArena Creative Writing14401419
LMArena Multi-Turn14711445
EQ-Bench Creative Writing—1559

Frequently asked questions

Is ERNIE 5.1 better than Gemini 3.5 Flash Lite?

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 41.8 on the Noometry Index.

Is ERNIE 5.1 or Gemini 3.5 Flash Lite better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 42.1 in the Noometry coding category.

How many benchmarks do ERNIE 5.1 and Gemini 3.5 Flash Lite share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Gemini 3.5 Flash Lite has 38.

Related comparisons

Go deeper