Noometry

Model comparison

ERNIE 5.1 vs Gemini 2.5 Flash-Lite

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 37.0 on the Noometry Index.

Last verified . 17 shared benchmarks.

ERNIE 5.1 Baidu

43.8

Rank #83 Confirmed

Gemini 2.5 Flash-Lite Google

37.0

Rank #211 Confirmed

Summary

  • They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Gemini 2.5 Flash-Lite in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in long context, where ERNIE 5.1 leads 44.7 to 33.3.

Side by side

ERNIE 5.1Gemini 2.5 Flash-Lite
ProviderBaiduGoogle
Noometry Index43.837.0
Released—2025-06-17
WeightsProprietaryProprietary
Context window—1.05M
Max output—66K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.40
Results tracked1933

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

Category by category

Coding ERNIE 5.1 leads

ERNIE 5.1: 44.0 (#76), Gemini 2.5 Flash-Lite: 38.5 (#173)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Coding14881373
WeirdML—35.2%
ALE-Bench—325.9

Agentic & Tool Use Not comparable

ERNIE 5.1: —, Gemini 2.5 Flash-Lite: 28.0 (#96)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
Berkeley Function Calling Leaderboard—36.9%
LMArena Search1227—

Reasoning Too close to call

ERNIE 5.1: 21.9 (#211), Gemini 2.5 Flash-Lite: 22.2 (#205)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Hard Prompts14811377
Kagi LLM Benchmark—40.5%
NYT Connections (extended)23.4%—
DTBench—62.8%
LMCA—18.1%
Epoch Capabilities Index—133.94

Math ERNIE 5.1 leads

ERNIE 5.1: 40.3 (#92), Gemini 2.5 Flash-Lite: 38.0 (#144)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Math14811373
Omni-MATH—48%

Knowledge ERNIE 5.1 leads

ERNIE 5.1: 41.9 (#102), Gemini 2.5 Flash-Lite: 32.5 (#210)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Expert14921373
MMLU-Pro—53.7%
Vectara Hallucination Rate—3.3%
GPQA (HELM)—30.9%

Multimodal Not comparable

ERNIE 5.1: —, Gemini 2.5 Flash-Lite: 29.1 (#114)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Vision—1198
VPCT—30%

Multilingual ERNIE 5.1 leads

ERNIE 5.1: 55.5 (#29), Gemini 2.5 Flash-Lite: 49.3 (#134)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Non-English14541369
LMArena Chinese15081404
LMArena French14881388
LMArena German14701389
LMArena Japanese14221359
LMArena Korean14271360
LMArena Russian14591373
LMArena Spanish14731396

Instruction Following ERNIE 5.1 leads

ERNIE 5.1: 76.7 (#37), Gemini 2.5 Flash-Lite: 70.0 (#168)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Instruction Following14601367
IFEval—81%

Long Context ERNIE 5.1 leads

ERNIE 5.1: 44.7 (#59), Gemini 2.5 Flash-Lite: 33.3 (#262)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Longer Query14621373
Fiction.LiveBench—47.2%

Writing & Preference ERNIE 5.1 leads

ERNIE 5.1: 65.1 (#52), Gemini 2.5 Flash-Lite: 56.8 (#135)

BenchmarkERNIE 5.1Gemini 2.5 Flash-Lite
LMArena Text14681379
LMArena Creative Writing14411367
LMArena Multi-Turn14711366
WildBench—81.8%

Frequently asked questions

Is ERNIE 5.1 better than Gemini 2.5 Flash-Lite?

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 37.0 on the Noometry Index.

Is ERNIE 5.1 or Gemini 2.5 Flash-Lite better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 38.5 in the Noometry coding category.

How many benchmarks do ERNIE 5.1 and Gemini 2.5 Flash-Lite share?

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.

Related comparisons

Go deeper