Noometry

Model comparison

ERNIE 5.1 vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.9 to 43.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

ERNIE 5.1 Baidu

43.8

Rank #83 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 4 categories and Grok 4.6 in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 21.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 80% for Grok 4.6.

Side by side

ERNIE 5.1Grok 4.6
ProviderBaiduxAI
Noometry Index43.856.9
Released—2026-08-12
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked1949

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

Category by category

Coding Grok 4.6 leads

ERNIE 5.1: 44.0 (#76), Grok 4.6: 58.5 (#16)

BenchmarkERNIE 5.1Grok 4.6
LMArena Coding14881465
DeepSWE—67.5%
FrontierCode—48%
CursorBench—41.4%
LMArena WebDev—1617
FrontierSWE—25.3%
SciCode—56.5%
WeirdML—67.3%
ALE-Bench—1,508

Agentic & Tool Use Not comparable

ERNIE 5.1: —, Grok 4.6: 39.4 (#27)

BenchmarkERNIE 5.1Grok 4.6
APEX-Agents—65.3%
GDP.pdf—17.2%
LMArena Search1227—
Vending-Bench 2—9,047

Reasoning Grok 4.6 leads

ERNIE 5.1: 21.9 (#211), Grok 4.6: 61.4 (#20)

BenchmarkERNIE 5.1Grok 4.6
NYT Connections (extended)23.4%80%
LMArena Hard Prompts14811447
ARC-AGI-2—67.1%
SimpleBench—75.9%
ARC-AGI-1—87.5%
CritPt—19.7%
Chess Puzzles—40%
EBR-Bench—30.5%
Mystery Game Puzzles—34%
DTBench—97.3%
LMCA—48.5%
Epoch Capabilities Index—156.44

Math Grok 4.6 leads

ERNIE 5.1: 40.3 (#92), Grok 4.6: 67.0 (#24)

BenchmarkERNIE 5.1Grok 4.6
LMArena Math14811423
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
OTIS Mock AIME 2024-2025—99.2%
ProofBench—51%

Knowledge Grok 4.6 leads

ERNIE 5.1: 41.9 (#102), Grok 4.6: 63.3 (#20)

BenchmarkERNIE 5.1Grok 4.6
LMArena Expert14921467
GPQA Diamond—94%
SimpleQA Verified—49.3%

Multimodal Not comparable

ERNIE 5.1: —, Grok 4.6: 43.6 (#23)

BenchmarkERNIE 5.1Grok 4.6
LMArena Vision—1263
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual ERNIE 5.1 leads

ERNIE 5.1: 55.5 (#29), Grok 4.6: 53.0 (#74)

BenchmarkERNIE 5.1Grok 4.6
LMArena Non-English14541420
LMArena Chinese15081480
LMArena French14881461
LMArena German14701431
LMArena Japanese14221376
LMArena Korean14271397
LMArena Russian14591422
LMArena Spanish14731404

Instruction Following ERNIE 5.1 leads

ERNIE 5.1: 76.7 (#37), Grok 4.6: 75.4 (#63)

BenchmarkERNIE 5.1Grok 4.6
LMArena Instruction Following14601431

Long Context Too close to call

ERNIE 5.1: 44.7 (#59), Grok 4.6: 44.5 (#66)

BenchmarkERNIE 5.1Grok 4.6
LMArena Longer Query14621454

Writing & Preference ERNIE 5.1 leads

ERNIE 5.1: 65.1 (#52), Grok 4.6: 62.3 (#80)

BenchmarkERNIE 5.1Grok 4.6
LMArena Text14681428
LMArena Creative Writing14411428
LMArena Multi-Turn14711425

Frequently asked questions

Is ERNIE 5.1 better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 43.8 on the Noometry Index.

Is ERNIE 5.1 or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 44.0 in the Noometry coding category.

How many benchmarks do ERNIE 5.1 and Grok 4.6 share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper