Noometry

Model comparison

ERNIE 5.0 0110 vs gpt-oss-20b

ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 32.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

ERNIE 5.0 0110 Baidu

41.8

Rank #129 Confirmed

gpt-oss-20b OpenAI

32.5

Rank #255 Confirmed

Summary

  • They share 16 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 6 categories and gpt-oss-20b in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.1 to 35.5.
  • gpt-oss-20b has downloadable open weights; the other is API-only.

Side by side

ERNIE 5.0 0110gpt-oss-20b
ProviderBaiduOpenAI
Noometry Index41.832.5
Released—2025-08-05
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.018
Output $ / M tokens—$0.09
Results tracked2034

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), gpt-oss-20b: 37.6 (#192)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Coding14551306
SciCode—34.4%
WeirdML—40.9%
ALE-Bench—566.05

Agentic & Tool Use Not comparable

ERNIE 5.0 0110: —, gpt-oss-20b: 9.3 (#154)

BenchmarkERNIE 5.0 0110gpt-oss-20b
Terminal-Bench—3.4%

Reasoning gpt-oss-20b leads

ERNIE 5.0 0110: 17.0 (#297), gpt-oss-20b: 19.3 (#261)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Hard Prompts14451274
Kagi LLM Benchmark—53.2%
NYT Connections (extended)10.3%—
CritPt—1.4%
Chess Puzzles—4%
Thematic Generalization41.7%—
DTBench—68%
LMCA—14.5%
Epoch Capabilities Index—137.82

Math Too close to call

ERNIE 5.0 0110: 39.3 (#110), gpt-oss-20b: 39.4 (#103)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Math14371317
OTIS Mock AIME 2024-2025—65.3%
Omni-MATH—56.5%

Knowledge ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 39.8 (#128), gpt-oss-20b: 34.6 (#195)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Expert14281258
GPQA Diamond—60.8%
MMLU-Pro—74%
GPQA (HELM)—59.4%

Multimodal Not comparable

ERNIE 5.0 0110: 39.9 (#53), gpt-oss-20b: —

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Vision1249—

Multilingual ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 54.1 (#49), gpt-oss-20b: 42.2 (#197)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Non-English14361268
LMArena Chinese15121314
LMArena German14601255
LMArena Japanese13821244
LMArena Korean14061236
LMArena Russian14461278
LMArena Spanish14731267
LMArena French1467—

Instruction Following ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 74.5 (#92), gpt-oss-20b: 61.8 (#240)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Instruction Following14131236
IFEval—73.2%

Long Context ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 43.4 (#95), gpt-oss-20b: 37.9 (#209)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Longer Query14221250

Writing & Preference ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 63.1 (#66), gpt-oss-20b: 35.5 (#265)

BenchmarkERNIE 5.0 0110gpt-oss-20b
LMArena Text14451287
LMArena Creative Writing14261201
LMArena Multi-Turn14341268
EQ-Bench Creative Writing—666
WildBench—73.7%

Frequently asked questions

Is ERNIE 5.0 0110 better than gpt-oss-20b?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 32.5 on the Noometry Index.

Is ERNIE 5.0 0110 or gpt-oss-20b better for coding?

ERNIE 5.0 0110 scores higher on coding benchmarks: 43.0 versus 37.6 in the Noometry coding category.

How many benchmarks do ERNIE 5.0 0110 and gpt-oss-20b share?

16 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and gpt-oss-20b has 34.

Related comparisons

Go deeper