Noometry

Model comparison

ERNIE 5.0 0110 vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

ERNIE 5.0 0110 Baidu

41.8

Rank #129 Confirmed

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Summary

  • They share 19 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 4 categories and GPT-6 Luna in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 39.3.
  • The biggest single-benchmark swing is NYT Connections (extended): 10.3% for ERNIE 5.0 0110 and 68.7% for GPT-6 Luna.

Side by side

ERNIE 5.0 0110GPT-6 Luna
ProviderBaiduOpenAI
Noometry Index41.853.3
Released—2026-09-22
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.50
Results tracked2042

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

Category by category

Coding GPT-6 Luna leads

ERNIE 5.0 0110: 43.0 (#94), GPT-6 Luna: 55.5 (#25)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Coding14551439
DeepSWE—66.6%
FrontierCode—42.4%
LMArena WebDev—1581
SciCode—54.6%
ALE-Bench—1,577

Agentic & Tool Use Not comparable

ERNIE 5.0 0110: —, GPT-6 Luna: 33.3 (#54)

BenchmarkERNIE 5.0 0110GPT-6 Luna
APEX-Agents—44.3%
GDP.pdf—23%

Reasoning GPT-6 Luna leads

ERNIE 5.0 0110: 17.0 (#297), GPT-6 Luna: 48.2 (#41)

BenchmarkERNIE 5.0 0110GPT-6 Luna
NYT Connections (extended)10.3%68.7%
LMArena Hard Prompts14451411
ARC-AGI-2—59.3%
ARC-AGI-1—86.7%
CritPt—19.4%
Chess Puzzles—31%
Thematic Generalization41.7%—
Mystery Game Puzzles—7%
DTBench—90.1%
LMCA—44.5%
Epoch Capabilities Index—156.28

Math GPT-6 Luna leads

ERNIE 5.0 0110: 39.3 (#110), GPT-6 Luna: 76.1 (#15)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Math14371416
FrontierMath (Tiers 1-3)—78.9%
FrontierMath Tier 4—56.1%
OTIS Mock AIME 2024-2025—98.9%
ProofBench—64%

Knowledge GPT-6 Luna leads

ERNIE 5.0 0110: 39.8 (#128), GPT-6 Luna: 57.0 (#41)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Expert14281444
GPQA Diamond—90.5%
SimpleQA Verified—41.4%

Multimodal GPT-6 Luna leads

ERNIE 5.0 0110: 39.9 (#53), GPT-6 Luna: 42.4 (#30)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Vision12491217
Blueprint-Bench 2—31.2%
Furniture Assembly—44.2%

Multilingual ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 54.1 (#49), GPT-6 Luna: 50.5 (#117)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Non-English14361386
LMArena Chinese15121433
LMArena French14671420
LMArena German14601369
LMArena Japanese13821369
LMArena Korean14061360
LMArena Russian14461394
LMArena Spanish14731393

Instruction Following Too close to call

ERNIE 5.0 0110: 74.5 (#92), GPT-6 Luna: 74.3 (#99)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Instruction Following14131409

Long Context Too close to call

ERNIE 5.0 0110: 43.4 (#95), GPT-6 Luna: 43.0 (#111)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Longer Query14221409

Writing & Preference ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 63.1 (#66), GPT-6 Luna: 58.3 (#119)

BenchmarkERNIE 5.0 0110GPT-6 Luna
LMArena Text14451391
LMArena Creative Writing14261363
LMArena Multi-Turn14341396

Frequently asked questions

Is ERNIE 5.0 0110 better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.8 on the Noometry Index.

Is ERNIE 5.0 0110 or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 43.0 in the Noometry coding category.

How many benchmarks do ERNIE 5.0 0110 and GPT-6 Luna share?

19 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and GPT-6 Luna has 42.

Related comparisons

Go deeper