Noometry

Model comparison

Claude Haiku 4.5 vs ERNIE 5.0 0110

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 39.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.3

Rank #155 Confirmed

ERNIE 5.0 0110 Baidu

41.2

Rank #129 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 3 categories and ERNIE 5.0 0110 in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in multimodal, where ERNIE 5.0 0110 leads 39.1 to 27.0.

Side by side

Claude Haiku 4.5ERNIE 5.0 0110
ProviderAnthropicBaidu
Noometry Index39.341.2
Released2025-10-15—
WeightsProprietaryProprietary
Context window200K—
Max output64K—
Input $ / M tokens$1—
Output $ / M tokens$5—
Results tracked5320

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

Category by category

Coding Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.9 (#71), ERNIE 5.0 0110: 42.3 (#94)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Coding14541455
SWE-bench Verified (bash only)66.6%—
LMArena WebDev1330—
SWE-bench Multilingual64.7%—
SciCode43.3%—
WeirdML45.4%—
ALE-Bench653.48—

Agentic & Tool Use Not comparable

Claude Haiku 4.5: 33.5 (#50), ERNIE 5.0 0110: —

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
Terminal-Bench35.5%—
Berkeley Function Calling Leaderboard68.7%—
DeepResearch Bench45.5%—
BALROG31.2%—
ExploitBench13.7%—
Vending-Bench 2458.89—

Reasoning ERNIE 5.0 0110 leads

Claude Haiku 4.5: 15.1 (#310), ERNIE 5.0 0110: 16.3 (#296)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
NYT Connections (extended)14.3%10.3%
LMArena Hard Prompts14201446
ARC-AGI-24%—
ARC-AGI-147.7%—
CritPt0%—
Chess Puzzles8%—
Thematic Generalization—41.7%
DTBench73.6%—
LMCA30.9%—
Epoch Capabilities Index142.42—
ForecastBench61.4—

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.0 (#69), ERNIE 5.0 0110: 36.5 (#111)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Math13951437
OTIS Mock AIME 2024-202566.7%—
Omni-MATH56.1%—
MATH Level 596.4%—
FrontierMath (Feb 2025 set)5.9%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge ERNIE 5.0 0110 leads

Claude Haiku 4.5: 37.6 (#146), ERNIE 5.0 0110: 39.2 (#125)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Expert14431427
GPQA Diamond71.2%—
SimpleQA Verified13.2%—
MMLU-Pro77.7%—
Vectara Hallucination Rate9.8%—
GPQA (HELM)60.5%—

Multimodal ERNIE 5.0 0110 leads

Claude Haiku 4.5: 27.0 (#111), ERNIE 5.0 0110: 39.1 (#49)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Vision—1248
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual ERNIE 5.0 0110 leads

Claude Haiku 4.5: 50.1 (#124), ERNIE 5.0 0110: 54.3 (#47)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Non-English13761436
LMArena Chinese14151512
LMArena French14081466
LMArena German13771462
LMArena Japanese13391383
LMArena Korean13461406
LMArena Russian13801446
LMArena Spanish14201473

Instruction Following ERNIE 5.0 0110 leads

Claude Haiku 4.5: 71.6 (#144), ERNIE 5.0 0110: 74.7 (#88)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Instruction Following14141413
IFEval80.1%—

Long Context Too close to call

Claude Haiku 4.5: 43.6 (#86), ERNIE 5.0 0110: 43.4 (#90)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Longer Query14271422

Writing & Preference ERNIE 5.0 0110 leads

Claude Haiku 4.5: 58.1 (#119), ERNIE 5.0 0110: 63.4 (#64)

BenchmarkClaude Haiku 4.5ERNIE 5.0 0110
LMArena Text13961445
LMArena Creative Writing13711426
LMArena Multi-Turn14091433
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than ERNIE 5.0 0110?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 39.3 on the Noometry Index.

Is Claude Haiku 4.5 or ERNIE 5.0 0110 better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 42.3 in the Noometry coding category.

How many benchmarks do Claude Haiku 4.5 and ERNIE 5.0 0110 share?

18 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and ERNIE 5.0 0110 has 20.

Related comparisons

Go deeper