Noometry

Model comparison

ERNIE 5.1 vs Kimi K2.5

Kimi K2.5 is the stronger model overall, scoring 47.8 to 43.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

ERNIE 5.1 Baidu

43.1

Rank #87 Confirmed

Kimi K2.5 Moonshot AI

47.8

Rank #50 Confirmed

Summary

  • They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 3 categories and Kimi K2.5 in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.5 leads 50.3 to 37.5.
  • The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 69.9% for Kimi K2.5.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

ERNIE 5.1Kimi K2.5
ProviderBaiduMoonshot AI
Noometry Index43.147.8
Released—2026-01-27
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.45
Output $ / M tokens—$2.25
Results tracked1951

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

Category by category

Coding Kimi K2.5 leads

ERNIE 5.1: 43.4 (#78), Kimi K2.5: 48.7 (#48)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Coding14881474
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—70.8%
LMArena WebDev—1436
SWE-bench Multilingual—67.3%
SciCode—49%
WeirdML—45.6%
ALE-Bench—821.65

Agentic & Tool Use Not comparable

ERNIE 5.1: —, Kimi K2.5: 34.0 (#44)

BenchmarkERNIE 5.1Kimi K2.5
Terminal-Bench—43.2%
OSWorld—63.3%
LMArena Search1227—
Vending-Bench 2—1,198

Reasoning Kimi K2.5 leads

ERNIE 5.1: 20.9 (#209), Kimi K2.5: 31.2 (#74)

BenchmarkERNIE 5.1Kimi K2.5
NYT Connections (extended)23.4%69.9%
LMArena Hard Prompts14811454
ARC-AGI-2—11.8%
SimpleBench—46.8%
Kagi LLM Benchmark—78.5%
ARC-AGI-1—65.3%
CritPt—3.1%
Chess Puzzles—12%
EnigmaEval—3.4%
Thematic Generalization—69.4%
Epoch Capabilities Index—148.05

Math Kimi K2.5 leads

ERNIE 5.1: 37.5 (#96), Kimi K2.5: 50.3 (#46)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Math14811470
MathArena Final-Answer Competitions—62.3%
OTIS Mock AIME 2024-2025—92.2%
FrontierMath (Feb 2025 set)—27.9%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Kimi K2.5 leads

ERNIE 5.1: 41.2 (#103), Kimi K2.5: 53.6 (#52)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Expert14911466
GPQA Diamond—87.6%
Humanity's Last Exam—24.4%
SimpleQA Verified—34.3%
Vectara Hallucination Rate—14.2%

Multimodal Not comparable

ERNIE 5.1: —, Kimi K2.5: 40.4 (#37)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Vision—1269
LMArena Document—1430

Multilingual ERNIE 5.1 leads

ERNIE 5.1: 55.7 (#28), Kimi K2.5: 54.1 (#50)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Non-English14551433
LMArena Chinese15071495
LMArena French14861454
LMArena German14701441
LMArena Japanese14221422
LMArena Korean14281412
LMArena Russian14591436
LMArena Spanish14721450

Instruction Following ERNIE 5.1 leads

ERNIE 5.1: 76.9 (#35), Kimi K2.5: 75.5 (#60)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Instruction Following14601431

Long Context Kimi K2.5 leads

ERNIE 5.1: 44.7 (#56), Kimi K2.5: 52.1 (#7)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Longer Query14621445
Fiction.LiveBench—86.1%
CL-bench—19.3%
CL-bench Life—13.2%

Writing & Preference Too close to call

ERNIE 5.1: 65.3 (#50), Kimi K2.5: 65.3 (#51)

BenchmarkERNIE 5.1Kimi K2.5
LMArena Text14681445
LMArena Creative Writing14401423
LMArena Multi-Turn14711444
EQ-Bench Creative Writing—1579

Frequently asked questions

Is ERNIE 5.1 better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 43.1 on the Noometry Index.

Is ERNIE 5.1 or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 43.4 in the Noometry coding category.

How many benchmarks do ERNIE 5.1 and Kimi K2.5 share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper