Noometry

Model comparison

ERNIE 5.1 vs GPT-5.6 Luna

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 43.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

ERNIE 5.1 Baidu

43.8

Rank #83 Confirmed

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

Summary

  • They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 3 categories and GPT-5.6 Luna in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 40.3.
  • The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 69.4% for GPT-5.6 Luna.

Side by side

ERNIE 5.1GPT-5.6 Luna
ProviderBaiduOpenAI
Noometry Index43.854.6
Released—2026-07-09
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$0.20
Output $ / M tokens—$1.20
Results tracked1952

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

Category by category

Coding GPT-5.6 Luna leads

ERNIE 5.1: 44.0 (#76), GPT-5.6 Luna: 54.5 (#28)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Coding14881466
DeepSWE—67.2%
FrontierCode—39.8%
CursorBench—35.9%
LMArena WebDev—1519
SciCode—53.6%
WeirdML—60.9%
ALE-Bench—1,667

Agentic & Tool Use Not comparable

ERNIE 5.1: —, GPT-5.6 Luna: 34.4 (#45)

BenchmarkERNIE 5.1GPT-5.6 Luna
APEX-Agents—43%
BALROG—45.6%
GDP.pdf—22.7%
LMArena Search1227—
Vending-Bench 2—4,095

Reasoning GPT-5.6 Luna leads

ERNIE 5.1: 21.9 (#211), GPT-5.6 Luna: 47.6 (#43)

BenchmarkERNIE 5.1GPT-5.6 Luna
NYT Connections (extended)23.4%69.4%
LMArena Hard Prompts14811451
ARC-AGI-2—59.5%
SimpleBench—46.8%
Kagi LLM Benchmark—49.1%
ARC-AGI-1—88%
CritPt—20.6%
Chess Puzzles—40%
Mystery Game Puzzles—21%
DTBench—89.1%
LMCA—48.5%
Surface Evolver Bench—61.9%
Epoch Capabilities Index—156.39

Math GPT-5.6 Luna leads

ERNIE 5.1: 40.3 (#92), GPT-5.6 Luna: 77.7 (#14)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Math14811458
FrontierMath (Tiers 1-3)—82.1%
FrontierMath Tier 4—61%
OTIS Mock AIME 2024-2025—98.3%
ProofBench—60%

Knowledge GPT-5.6 Luna leads

ERNIE 5.1: 41.9 (#102), GPT-5.6 Luna: 58.5 (#34)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Expert14921478
GPQA Diamond—91.6%
SimpleQA Verified—41%

Multimodal Not comparable

ERNIE 5.1: —, GPT-5.6 Luna: 42.7 (#28)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Vision—1258
Blueprint-Bench 2—22.6%
Furniture Assembly—42.5%
LMArena Document—1457

Multilingual ERNIE 5.1 leads

ERNIE 5.1: 55.5 (#29), GPT-5.6 Luna: 52.8 (#78)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Non-English14541417
LMArena Chinese15081470
LMArena French14881456
LMArena German14701454
LMArena Japanese14221411
LMArena Korean14271415
LMArena Russian14591428
LMArena Spanish14731448

Instruction Following ERNIE 5.1 leads

ERNIE 5.1: 76.7 (#37), GPT-5.6 Luna: 75.6 (#57)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Instruction Following14601437

Long Context Too close to call

ERNIE 5.1: 44.7 (#59), GPT-5.6 Luna: 43.9 (#82)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Longer Query14621436

Writing & Preference GPT-5.6 Luna leads

ERNIE 5.1: 65.1 (#52), GPT-5.6 Luna: 68.0 (#29)

BenchmarkERNIE 5.1GPT-5.6 Luna
LMArena Text14681431
LMArena Creative Writing14411396
LMArena Multi-Turn14711434
EQ-Bench Creative Writing—1829
EQ-Bench 4—1156

Frequently asked questions

Is ERNIE 5.1 better than GPT-5.6 Luna?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 43.8 on the Noometry Index.

Is ERNIE 5.1 or GPT-5.6 Luna better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 44.0 in the Noometry coding category.

How many benchmarks do ERNIE 5.1 and GPT-5.6 Luna share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-5.6 Luna has 52.

Related comparisons

Go deeper