Noometry

Model comparison

ERNIE 5.1 vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 61.8 to 43.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

ERNIE 5.1 Baidu

43.8

Rank #83 Confirmed

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 3 categories and GPT-6 Sol in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 21.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 90.1% for GPT-6 Sol.

Side by side

ERNIE 5.1GPT-6 Sol
ProviderBaiduOpenAI
Noometry Index43.861.8
Released—2026-09-22
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked1945

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

Category by category

Coding GPT-6 Sol leads

ERNIE 5.1: 44.0 (#76), GPT-6 Sol: 60.1 (#11)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Coding14881447
DeepSWE—68.8%
FrontierCode—49.3%
LMArena WebDev—1688
SciCode—57.6%
ALE-Bench—2,462

Agentic & Tool Use Not comparable

ERNIE 5.1: —, GPT-6 Sol: 37.2 (#36)

BenchmarkERNIE 5.1GPT-6 Sol
APEX-Agents—54.3%
GDP.pdf—26.4%
LMArena Search1227—
Vending-Bench 2—14,428

Reasoning GPT-6 Sol leads

ERNIE 5.1: 21.9 (#211), GPT-6 Sol: 74.0 (#9)

BenchmarkERNIE 5.1GPT-6 Sol
NYT Connections (extended)23.4%90.1%
LMArena Hard Prompts14811418
ARC-AGI-2—89.6%
ARC-AGI-1—95.5%
CritPt—30.9%
EBR-Bench—53.3%
Mystery Game Puzzles—56%
DTBench—97.3%
LMCA—59.1%
Epoch Capabilities Index—162.72

Math GPT-6 Sol leads

ERNIE 5.1: 40.3 (#92), GPT-6 Sol: 87.2 (#7)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Math14811402
FrontierMath (Tiers 1-3)—89.8%
FrontierMath Tier 4—90%
OTIS Mock AIME 2024-2025—100%
ProofBench—83%

Knowledge GPT-6 Sol leads

ERNIE 5.1: 41.9 (#102), GPT-6 Sol: 64.8 (#15)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Expert14921439
GPQA Diamond—94.3%
SimpleQA Verified—60.7%
Vectara Hallucination Rate—6.5%

Multimodal Not comparable

ERNIE 5.1: —, GPT-6 Sol: 47.6 (#10)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Vision—1245
Blueprint-Bench 2—36.9%
Furniture Assembly—58.3%

Multilingual ERNIE 5.1 leads

ERNIE 5.1: 55.5 (#29), GPT-6 Sol: 50.5 (#118)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Non-English14541385
LMArena Chinese15081405
LMArena French14881410
LMArena German14701390
LMArena Japanese14221385
LMArena Korean14271341
LMArena Russian14591401
LMArena Spanish14731384

Instruction Following ERNIE 5.1 leads

ERNIE 5.1: 76.7 (#37), GPT-6 Sol: 74.5 (#94)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Instruction Following14601412

Long Context ERNIE 5.1 leads

ERNIE 5.1: 44.7 (#59), GPT-6 Sol: 43.1 (#108)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Longer Query14621411

Writing & Preference GPT-6 Sol leads

ERNIE 5.1: 65.1 (#52), GPT-6 Sol: 71.9 (#18)

BenchmarkERNIE 5.1GPT-6 Sol
LMArena Text14681395
LMArena Creative Writing14411378
LMArena Multi-Turn14711412
EQ-Bench Creative Writing—2125

Frequently asked questions

Is ERNIE 5.1 better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 43.8 on the Noometry Index.

Is ERNIE 5.1 or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 44.0 in the Noometry coding category.

How many benchmarks do ERNIE 5.1 and GPT-6 Sol share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper