Noometry

Model comparison

ERNIE 5.0 0110 vs Kimi K3

Kimi K3 is the stronger model overall, scoring 59.5 to 41.2 on the Noometry Index.

Last verified . 18 shared benchmarks.

ERNIE 5.0 0110 Baidu

41.2

Rank #129 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #12 Confirmed

Summary

  • They share 18 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 1 category and Kimi K3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Kimi K3 leads 63.0 to 16.3.
  • The biggest single-benchmark swing is NYT Connections (extended): 10.3% for ERNIE 5.0 0110 and 93.6% for Kimi K3.
  • Kimi K3 has downloadable open weights; the other is API-only.

Side by side

ERNIE 5.0 0110Kimi K3
ProviderBaiduMoonshot AI
Noometry Index41.259.5
Released—2026-07-16
WeightsProprietaryOpen
Context window—1.05M
Max output—1.05M
Input $ / M tokens—$3
Output $ / M tokens—$15
Results tracked2053

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

Category by category

Coding Kimi K3 leads

ERNIE 5.0 0110: 42.3 (#94), Kimi K3: 60.6 (#8)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Coding14551509
DeepSWE—68.5%
FrontierCode—44.2%
LMArena WebDev—1659
FrontierSWE—25.9%
SciCode—59.5%
WeirdML—82.6%
ALE-Bench—1,524

Agentic & Tool Use Not comparable

ERNIE 5.0 0110: —, Kimi K3: 41.8 (#19)

BenchmarkERNIE 5.0 0110Kimi K3
APEX-Agents—50.6%
τ²-bench Banking—37.1%
PostTrainBench—32%
GBAEval—48.3%
GDP.pdf—19%
Vending-Bench 2—5,165

Reasoning Kimi K3 leads

ERNIE 5.0 0110: 16.3 (#296), Kimi K3: 63.0 (#15)

BenchmarkERNIE 5.0 0110Kimi K3
NYT Connections (extended)10.3%93.6%
LMArena Hard Prompts14461495
ARC-AGI-2—60.4%
SimpleBench—60.7%
ARC-AGI-1—94.5%
CritPt—23.4%
Chess Puzzles—39%
Thematic Generalization41.7%—
Mystery Game Puzzles—26%
DTBench—91.2%
LMCA—52.7%
Surface Evolver Bench—95%
Epoch Capabilities Index—157.68
ForecastBench—61.1

Math Kimi K3 leads

ERNIE 5.0 0110: 36.5 (#111), Kimi K3: 74.0 (#13)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Math14371493
FrontierMath (Tiers 1-3)—72.2%
FrontierMath Tier 4—39%
MathArena Final-Answer Competitions—87.8%
OTIS Mock AIME 2024-2025—97.2%
ProofBench—87%

Knowledge Kimi K3 leads

ERNIE 5.0 0110: 39.2 (#125), Kimi K3: 63.2 (#19)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Expert14271520
GPQA Diamond—93.1%
SimpleQA Verified—50.6%

Multimodal Too close to call

ERNIE 5.0 0110: 39.1 (#49), Kimi K3: 38.4 (#58)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Vision1248—
Blueprint-Bench 2—29.5%
Furniture Assembly—34.2%

Multilingual Kimi K3 leads

ERNIE 5.0 0110: 54.3 (#47), Kimi K3: 56.5 (#20)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Non-English14361466
LMArena Chinese15121528
LMArena French14661488
LMArena German14621474
LMArena Japanese13831492
LMArena Korean14061465
LMArena Russian14461481
LMArena Spanish14731478

Instruction Following Kimi K3 leads

ERNIE 5.0 0110: 74.7 (#88), Kimi K3: 77.8 (#13)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Instruction Following14131481

Long Context Kimi K3 leads

ERNIE 5.0 0110: 43.4 (#90), Kimi K3: 45.8 (#27)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Longer Query14221494

Writing & Preference Kimi K3 leads

ERNIE 5.0 0110: 63.4 (#64), Kimi K3: 76.7 (#4)

BenchmarkERNIE 5.0 0110Kimi K3
LMArena Text14451476
LMArena Creative Writing14261452
LMArena Multi-Turn14331488
EQ-Bench Creative Writing—2082
EQ-Bench 4—1339

Frequently asked questions

Is ERNIE 5.0 0110 better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 41.2 on the Noometry Index.

Is ERNIE 5.0 0110 or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 60.6 versus 42.3 in the Noometry coding category.

How many benchmarks do ERNIE 5.0 0110 and Kimi K3 share?

18 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper