Noometry

Model comparison

ERNIE 5.0 0110 vs Phi 3 Mini 4k Instruct

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 27.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

ERNIE 5.0 0110 Baidu

41.2

Rank #129 Confirmed

Phi 3 Mini 4k Instruct Microsoft

27.4

Rank #324 Confirmed

Summary

  • They share 17 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.4 to 27.7.
  • Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

Side by side

ERNIE 5.0 0110Phi 3 Mini 4k Instruct
ProviderBaiduMicrosoft
Noometry Index41.227.4
Released—2024-04-23
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2035

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

Category by category

Coding ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 42.3 (#94), Phi 3 Mini 4k Instruct: 26.1 (#319)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Coding14551093
LiveBench Coding—15.5%
HumanEval+—59.1%
MBPP+—54.2%

Reasoning ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 16.3 (#296), Phi 3 Mini 4k Instruct: 13.6 (#326)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Hard Prompts14461072
NYT Connections (extended)10.3%—
Chess Puzzles—0%
Thematic Generalization41.7%—
LiveBench Reasoning—26.8%
LiveBench Data Analysis—34.7%
Adversarial NLI—52.8%
BIG-Bench Hard—71.7%
HellaSwag—76.7%
LiveBench—22.4%
WinoGrande—70.8%

Math ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 36.5 (#111), Phi 3 Mini 4k Instruct: 24.5 (#258)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Math14371111
LiveBench Math—15.7%

Knowledge ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 39.2 (#125), Phi 3 Mini 4k Instruct: 27.9 (#241)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Expert14271045
ARC (AI2) Challenge—84.9%
MMLU—68.8%
OpenBookQA—88%
TriviaQA—64%

Multimodal Not comparable

ERNIE 5.0 0110: 39.1 (#49), Phi 3 Mini 4k Instruct: —

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Vision1248—

Multilingual ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 54.3 (#47), Phi 3 Mini 4k Instruct: 26.5 (#275)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Non-English14361021
LMArena Chinese15121021
LMArena French14661075
LMArena German14621044
LMArena Japanese1383935
LMArena Korean1406905
LMArena Russian14461022
LMArena Spanish14731084

Instruction Following ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 74.7 (#88), Phi 3 Mini 4k Instruct: 48.0 (#298)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Instruction Following14131053
LiveBench Instruction Following—39.1%

Long Context ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 43.4 (#90), Phi 3 Mini 4k Instruct: 31.7 (#271)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Longer Query14221044

Writing & Preference ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 63.4 (#64), Phi 3 Mini 4k Instruct: 27.7 (#295)

BenchmarkERNIE 5.0 0110Phi 3 Mini 4k Instruct
LMArena Text14451073
LMArena Creative Writing14261037
LMArena Multi-Turn14331018
LiveBench Language—9.2%

Frequently asked questions

Is ERNIE 5.0 0110 better than Phi 3 Mini 4k Instruct?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 27.4 on the Noometry Index.

Is ERNIE 5.0 0110 or Phi 3 Mini 4k Instruct better for coding?

ERNIE 5.0 0110 scores higher on coding benchmarks: 42.3 versus 26.1 in the Noometry coding category.

How many benchmarks do ERNIE 5.0 0110 and Phi 3 Mini 4k Instruct share?

17 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.

Related comparisons

Go deeper