Noometry

Model comparison

ERNIE 5.0 0110 vs GPT-5.4 mini

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 41.8 on the Noometry Index.

Last verified . 20 shared benchmarks.

ERNIE 5.0 0110 Baidu

41.8

Rank #129 Confirmed

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Summary

  • They share 20 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 4 categories and GPT-5.4 mini in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 mini leads 30.4 to 17.0.
  • The biggest single-benchmark swing is NYT Connections (extended): 10.3% for ERNIE 5.0 0110 and 61.8% for GPT-5.4 mini.

Side by side

ERNIE 5.0 0110GPT-5.4 mini
ProviderBaiduOpenAI
Noometry Index41.845.0
Released—2026-03-17
WeightsProprietaryProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$0.75
Output $ / M tokens—$4.50
Results tracked2046

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

Category by category

Coding GPT-5.4 mini leads

ERNIE 5.0 0110: 43.0 (#94), GPT-5.4 mini: 45.2 (#72)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Coding14551438
FrontierCode—27%
LMArena WebDev—1397
SciCode—49.9%
WeirdML—60.3%
ALE-Bench—1,189

Agentic & Tool Use Not comparable

ERNIE 5.0 0110: —, GPT-5.4 mini: 29.9 (#81)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
DeepResearch Bench—36.3%

Reasoning GPT-5.4 mini leads

ERNIE 5.0 0110: 17.0 (#297), GPT-5.4 mini: 30.4 (#85)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
NYT Connections (extended)10.3%61.8%
Thematic Generalization41.7%61.7%
LMArena Hard Prompts14451424
ARC-AGI-2—18.9%
Kagi LLM Benchmark—37.9%
ARC-AGI-1—63.7%
CritPt—10%
Chess Puzzles—24%
Mystery Game Puzzles—11%
DTBench—80%
LMCA—40.8%
Epoch Capabilities Index—148.84
ForecastBench—57

Math GPT-5.4 mini leads

ERNIE 5.0 0110: 39.3 (#110), GPT-5.4 mini: 45.5 (#75)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Math14371419
FrontierMath (Tiers 1-3)—51.2%
FrontierMath Tier 4—9.8%
OTIS Mock AIME 2024-2025—88.9%
ProofBench—21%
FrontierMath (Feb 2025 set)—28.3%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GPT-5.4 mini leads

ERNIE 5.0 0110: 39.8 (#128), GPT-5.4 mini: 51.5 (#67)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Expert14281435
GPQA Diamond—86.9%
SimpleQA Verified—29.4%
Vectara Hallucination Rate—5.5%

Multimodal Too close to call

ERNIE 5.0 0110: 39.9 (#53), GPT-5.4 mini: 39.7 (#56)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Vision12491245

Multilingual ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 54.1 (#49), GPT-5.4 mini: 51.9 (#96)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Non-English14361405
LMArena Chinese15121446
LMArena French14671440
LMArena German14601409
LMArena Japanese13821374
LMArena Korean14061368
LMArena Russian14461417
LMArena Spanish14731405

Instruction Following Too close to call

ERNIE 5.0 0110: 74.5 (#92), GPT-5.4 mini: 74.1 (#102)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Instruction Following14131405

Long Context Too close to call

ERNIE 5.0 0110: 43.4 (#95), GPT-5.4 mini: 43.0 (#112)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Longer Query14221407

Writing & Preference Too close to call

ERNIE 5.0 0110: 63.1 (#66), GPT-5.4 mini: 64.0 (#58)

BenchmarkERNIE 5.0 0110GPT-5.4 mini
LMArena Text14451412
LMArena Creative Writing14261370
LMArena Multi-Turn14341429
EQ-Bench Creative Writing—1665

Frequently asked questions

Is ERNIE 5.0 0110 better than GPT-5.4 mini?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 41.8 on the Noometry Index.

Is ERNIE 5.0 0110 or GPT-5.4 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 43.0 in the Noometry coding category.

How many benchmarks do ERNIE 5.0 0110 and GPT-5.4 mini share?

20 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and GPT-5.4 mini has 46.

Related comparisons

Go deeper