Noometry

Model comparison

Claude Sonnet 4.6 vs ERNIE 5.1

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 43.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.1

Rank #42 Confirmed

ERNIE 5.1 Baidu

43.1

Rank #87 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 7 categories and ERNIE 5.1 in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 20.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 80.9% for Claude Sonnet 4.6 and 23.4% for ERNIE 5.1.

Side by side

Claude Sonnet 4.6ERNIE 5.1
ProviderAnthropicBaidu
Noometry Index50.143.1
Released2026-02-17—
WeightsProprietaryProprietary
Context window1M—
Max output128K—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked5719

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.0 (#62), ERNIE 5.1: 43.4 (#78)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Coding15041488
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1521—
SciCode46.8%—
WeirdML66.1%—
ALE-Bench1,327—

Agentic & Tool Use Not comparable

Claude Sonnet 4.6: 39.1 (#26), ERNIE 5.1: —

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Search12211227
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#40), ERNIE 5.1: 20.9 (#209)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
NYT Connections (extended)80.9%23.4%
LMArena Hard Prompts14851481
ARC-AGI-260.4%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
Thematic Generalization76.3%—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—
Epoch Capabilities Index152.25—
ForecastBench62—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.9 (#41), ERNIE 5.1: 37.5 (#96)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Math14631481
OTIS Mock AIME 2024-202585.8%—
ProofBench45%—
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.6 (#60), ERNIE 5.1: 41.2 (#103)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Expert15001491
GPQA Diamond87.4%—
SimpleQA Verified35.5%—
Vectara Hallucination Rate10.6%—

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#61), ERNIE 5.1: —

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual ERNIE 5.1 leads

Claude Sonnet 4.6: 54.6 (#39), ERNIE 5.1: 55.7 (#28)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Non-English14401455
LMArena Chinese14911507
LMArena French14651486
LMArena German14281470
LMArena Japanese14191422
LMArena Korean14111428
LMArena Russian14401459
LMArena Spanish14651472

Instruction Following Too close to call

Claude Sonnet 4.6: 77.6 (#23), ERNIE 5.1: 76.9 (#35)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Instruction Following14761460

Long Context Too close to call

Claude Sonnet 4.6: 45.3 (#40), ERNIE 5.1: 44.7 (#56)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Longer Query14791462

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.4 (#22), ERNIE 5.1: 65.3 (#50)

BenchmarkClaude Sonnet 4.6ERNIE 5.1
LMArena Text14581468
LMArena Creative Writing14351440
LMArena Multi-Turn14641471
EQ-Bench Creative Writing1810—
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than ERNIE 5.1?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 43.1 on the Noometry Index.

Is Claude Sonnet 4.6 or ERNIE 5.1 better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 43.4 in the Noometry coding category.

How many benchmarks do Claude Sonnet 4.6 and ERNIE 5.1 share?

19 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and ERNIE 5.1 has 19.

Related comparisons

Go deeper