Noometry

Model comparison

ERNIE 5.0 0110 vs Qwen2.5 72B Instruct

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 31.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

ERNIE 5.0 0110 Baidu

41.2

Rank #129 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.5

Rank #259 Confirmed

Summary

  • They share 17 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 7 categories and Qwen2.5 72B Instruct in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where ERNIE 5.0 0110 leads 36.5 to 18.1.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

ERNIE 5.0 0110Qwen2.5 72B Instruct
ProviderBaiduAlibaba (Qwen)
Noometry Index41.231.5
Released—2024-09
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$1.40
Output $ / M tokens—$5.60
Results tracked2043

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), Qwen2.5 72B Instruct: 32.8 (#256)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Coding14551293
WeirdML—16%
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%

Agentic & Tool Use Not comparable

ERNIE 5.0 0110: —, Qwen2.5 72B Instruct: 22.0 (#124)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
TheAgentCompany—5.7%
BALROG—16.2%
METR Time Horizons—35.8%

Reasoning Qwen2.5 72B Instruct leads

ERNIE 5.0 0110: 16.3 (#296), Qwen2.5 72B Instruct: 21.4 (#197)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Hard Prompts14461271
NYT Connections (extended)10.3%—
Thematic Generalization41.7%—
DTBench—62.9%
LMCA—13.4%
BIG-Bench Hard—79.8%
Epoch Capabilities Index—129.01
ForecastBench—57.5
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 36.5 (#111), Qwen2.5 72B Instruct: 18.1 (#281)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Math14371283
OTIS Mock AIME 2024-2025—8.1%
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 39.2 (#125), Qwen2.5 72B Instruct: 26.9 (#247)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Expert14271245
GPQA Diamond—49.1%
MMLU-Pro—63.1%
Confabulations—19.1%
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

ERNIE 5.0 0110: 39.1 (#49), Qwen2.5 72B Instruct: —

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Vision1248—

Multilingual ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 54.3 (#47), Qwen2.5 72B Instruct: 41.2 (#208)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Non-English14361252
LMArena Chinese15121272
LMArena French14661279
LMArena German14621234
LMArena Japanese13831180
LMArena Korean14061188
LMArena Russian14461264
LMArena Spanish14731255

Instruction Following ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 74.7 (#88), Qwen2.5 72B Instruct: 65.7 (#216)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Instruction Following14131254
IFEval—80.6%

Long Context ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 43.4 (#90), Qwen2.5 72B Instruct: 38.9 (#183)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Longer Query14221282

Writing & Preference ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 63.4 (#64), Qwen2.5 72B Instruct: 46.9 (#210)

BenchmarkERNIE 5.0 0110Qwen2.5 72B Instruct
LMArena Text14451269
LMArena Creative Writing14261221
LMArena Multi-Turn14331272
WildBench—80.2%

Frequently asked questions

Is ERNIE 5.0 0110 better than Qwen2.5 72B Instruct?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 31.5 on the Noometry Index.

Is ERNIE 5.0 0110 or Qwen2.5 72B Instruct better for coding?

ERNIE 5.0 0110 scores higher on coding benchmarks: 42.3 versus 32.8 in the Noometry coding category.

How many benchmarks do ERNIE 5.0 0110 and Qwen2.5 72B Instruct share?

17 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper