Noometry

Model comparison

ERNIE 5.1 vs GPT-5.4

GPT-5.4 is the stronger model overall, scoring 59.4 to 43.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

ERNIE 5.1 Baidu

43.8

Rank #83 Confirmed

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Summary

  • They share 19 benchmarks with published results for both. ERNIE 5.1 scores higher in 0 categories and GPT-5.4 in 8 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 leads 61.8 to 21.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 91.3% for GPT-5.4.

Side by side

ERNIE 5.1GPT-5.4
ProviderBaiduOpenAI
Noometry Index43.859.4
Released—2026-03-05
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2.50
Output $ / M tokens—$15
Results tracked1968

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

Category by category

Coding GPT-5.4 leads

ERNIE 5.1: 44.0 (#76), GPT-5.4: 52.6 (#33)

BenchmarkERNIE 5.1GPT-5.4
LMArena Coding14881497
SWE-bench Verified—76.9%
DeepSWE—51.8%
LMArena WebDev—1465
SciCode—56.6%
GSO—31.4%
WeirdML—77.7%
MirrorCode—15.6%
ALE-Bench—1,607
AlgoTune—1.85

Agentic & Tool Use Not comparable

ERNIE 5.1: —, GPT-5.4: 46.5 (#13)

BenchmarkERNIE 5.1GPT-5.4
LMArena Search12271197
Terminal-Bench—81.8%
APEX-Agents—52.4%
τ²-bench Banking—39.4%
DeepResearch Bench—35.1%
PostTrainBench—19%
GBAEval—45.1%
METR Time Horizons—74.3%
Vending-Bench 2—6,144

Reasoning GPT-5.4 leads

ERNIE 5.1: 21.9 (#211), GPT-5.4: 61.8 (#19)

BenchmarkERNIE 5.1GPT-5.4
NYT Connections (extended)23.4%91.3%
LMArena Hard Prompts14811485
ARC-AGI-2—74%
Kagi LLM Benchmark—63.8%
ARC-AGI-1—93.7%
CritPt—23.4%
Chess Puzzles—44%
EnigmaEval—16%
Thematic Generalization—80%
EBR-Bench—25.4%
Mystery Game Puzzles—37%
DTBench—94.4%
LMCA—52%
Epoch Capabilities Index—156.81
ForecastBench—59.5

Math GPT-5.4 leads

ERNIE 5.1: 40.3 (#92), GPT-5.4: 73.5 (#19)

BenchmarkERNIE 5.1GPT-5.4
LMArena Math14811488
FrontierMath (Tiers 1-3)—78.6%
FrontierMath Tier 4—49%
MathArena Final-Answer Competitions—83.1%
OTIS Mock AIME 2024-2025—97.8%
ProofBench—56%
FrontierMath (Feb 2025 set)—47.6%
FrontierMath Tier 4 (v1)—27.1%

Knowledge GPT-5.4 leads

ERNIE 5.1: 41.9 (#102), GPT-5.4: 65.3 (#14)

BenchmarkERNIE 5.1GPT-5.4
LMArena Expert14921507
GPQA Diamond—93.3%
Humanity's Last Exam—36.2%
SimpleQA Verified—45.1%
Vectara Hallucination Rate—7%

Multimodal Not comparable

ERNIE 5.1: —, GPT-5.4: 43.7 (#20)

BenchmarkERNIE 5.1GPT-5.4
LMArena Vision—1303
Blueprint-Bench 2—27.1%
Furniture Assembly—37.5%
LMArena Document—1471

Multilingual Too close to call

ERNIE 5.1: 55.5 (#29), GPT-5.4: 56.2 (#23)

BenchmarkERNIE 5.1GPT-5.4
LMArena Non-English14541465
LMArena Chinese15081519
LMArena French14881493
LMArena German14701472
LMArena Japanese14221485
LMArena Korean14271448
LMArena Russian14591480
LMArena Spanish14731454

Instruction Following Too close to call

ERNIE 5.1: 76.7 (#37), GPT-5.4: 77.1 (#27)

BenchmarkERNIE 5.1GPT-5.4
LMArena Instruction Following14601469

Long Context GPT-5.4 leads

ERNIE 5.1: 44.7 (#59), GPT-5.4: 50.3 (#8)

BenchmarkERNIE 5.1GPT-5.4
LMArena Longer Query14621473
CL-bench—27.9%
CL-bench Life—21.7%

Writing & Preference GPT-5.4 leads

ERNIE 5.1: 65.1 (#52), GPT-5.4: 71.9 (#17)

BenchmarkERNIE 5.1GPT-5.4
LMArena Text14681469
LMArena Creative Writing14411439
LMArena Multi-Turn14711482
EQ-Bench Creative Writing—1840
EQ-Bench 4—1272

Frequently asked questions

Is ERNIE 5.1 better than GPT-5.4?

GPT-5.4 is the stronger model overall, scoring 59.4 to 43.8 on the Noometry Index.

Is ERNIE 5.1 or GPT-5.4 better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.6 versus 44.0 in the Noometry coding category.

How many benchmarks do ERNIE 5.1 and GPT-5.4 share?

19 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-5.4 has 68.

Related comparisons

Go deeper