Noometry

Model comparison

ERNIE 5.0 0110 vs Granite 3.1 2b Instruct

ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 33.2 on the Noometry Index.

Last verified . 12 shared benchmarks.

ERNIE 5.0 0110 Baidu

41.8

Rank #129 Confirmed

Granite 3.1 2b Instruct IBM

33.2

Rank #247 Confirmed

Summary

  • They share 12 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 7 categories and Granite 3.1 2b Instruct in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.1 to 34.1.
  • Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.

Side by side

ERNIE 5.0 0110Granite 3.1 2b Instruct
ProviderBaiduIBM
Noometry Index41.833.2
Released——
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2012

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: 43.0 (#94), Granite 3.1 2b Instruct: 33.4 (#257)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Coding14551149

Reasoning Granite 3.1 2b Instruct leads

ERNIE 5.0 0110: 17.0 (#297), Granite 3.1 2b Instruct: 22.0 (#209)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Hard Prompts14451138
NYT Connections (extended)10.3%—
Thematic Generalization41.7%—

Math ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 39.3 (#110), Granite 3.1 2b Instruct: 33.1 (#206)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Math14371159

Knowledge ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 39.8 (#128), Granite 3.1 2b Instruct: 30.8 (#224)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Expert14281131

Multimodal Not comparable

ERNIE 5.0 0110: 39.9 (#53), Granite 3.1 2b Instruct: —

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Vision1249—

Multilingual ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 54.1 (#49), Granite 3.1 2b Instruct: 29.1 (#269)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Non-English14361068
LMArena Chinese15121139
LMArena Russian14461063
LMArena French1467—
LMArena German1460—
LMArena Japanese1382—
LMArena Korean1406—
LMArena Spanish1473—

Instruction Following ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 74.5 (#92), Granite 3.1 2b Instruct: 57.7 (#264)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Instruction Following14131116

Long Context ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 43.4 (#95), Granite 3.1 2b Instruct: 35.0 (#244)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Longer Query14221155

Writing & Preference ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 63.1 (#66), Granite 3.1 2b Instruct: 34.1 (#274)

BenchmarkERNIE 5.0 0110Granite 3.1 2b Instruct
LMArena Text14451127
LMArena Creative Writing14261116
LMArena Multi-Turn14341099

Frequently asked questions

Is ERNIE 5.0 0110 better than Granite 3.1 2b Instruct?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 33.2 on the Noometry Index.

Is ERNIE 5.0 0110 or Granite 3.1 2b Instruct better for coding?

ERNIE 5.0 0110 scores higher on coding benchmarks: 43.0 versus 33.4 in the Noometry coding category.

How many benchmarks do ERNIE 5.0 0110 and Granite 3.1 2b Instruct share?

12 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Granite 3.1 2b Instruct has 12.

Related comparisons

Go deeper