Noometry

Model comparison

Claude Haiku 4.5 vs Yi-Lightning

Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 36.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.3

Rank #155 Confirmed

Yi-Lightning 01.AI

36.5

Rank #206 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Yi-Lightning in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Haiku 4.5 leads 43.9 to 27.0.

Side by side

Claude Haiku 4.5Yi-Lightning
ProviderAnthropic01.AI
Noometry Index39.336.5
Released2025-10-152024-12-02
WeightsProprietaryProprietary
Context window200K—
Max output64K—
Input $ / M tokens$1—
Output $ / M tokens$5—
Results tracked5318

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), Yi-Lightning: 27.0 (#315)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Coding14541313
SWE-bench Verified (bash only)66.6%—
Aider Polyglot—12.9%
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), Yi-Lightning: —

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

Reasoning Yi-Lightning leads

Claude Haiku 4.5: 15.1 (#310), Yi-Lightning: 24.9 (#137)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Hard Prompts14201302
ARC-AGI-24%—
NYT Connections (extended)14.3%—
ARC-AGI-147.7%—
CritPt0%—
Chess Puzzles8%—
DTBench73.6%—
LMCA30.9%—
Epoch Capabilities Index142.42—
ForecastBench61.4—

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.0 (#69), Yi-Lightning: 33.5 (#173)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Math13951300
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 Claude Haiku 4.5 leads

Claude Haiku 4.5: 37.6 (#146), Yi-Lightning: 34.8 (#182)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Expert14431286
GPQA Diamond71.2%—
SimpleQA Verified13.2%—
MMLU-Pro77.7%—
Vectara Hallucination Rate9.8%—
GPQA (HELM)60.5%—

Multimodal Not comparable

Claude Haiku 4.5: 27.0 (#111), Yi-Lightning: —

BenchmarkClaude Haiku 4.5Yi-Lightning
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual Claude Haiku 4.5 leads

Claude Haiku 4.5: 50.1 (#124), Yi-Lightning: 42.4 (#191)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Non-English13761269
LMArena Chinese14151320
LMArena French14081304
LMArena German13771267
LMArena Japanese13391228
LMArena Korean13461192
LMArena Russian13801255
LMArena Spanish14201315

Instruction Following Claude Haiku 4.5 leads

Claude Haiku 4.5: 71.6 (#144), Yi-Lightning: 67.6 (#191)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Instruction Following14141278
IFEval80.1%—

Long Context Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.6 (#86), Yi-Lightning: 39.4 (#176)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Longer Query14271297

Writing & Preference Claude Haiku 4.5 leads

Claude Haiku 4.5: 58.1 (#119), Yi-Lightning: 50.4 (#178)

BenchmarkClaude Haiku 4.5Yi-Lightning
LMArena Text13961302
LMArena Creative Writing13711280
LMArena Multi-Turn14091311
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than Yi-Lightning?

Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 36.5 on the Noometry Index.

Is Claude Haiku 4.5 or Yi-Lightning better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 27.0 in the Noometry coding category.

How many benchmarks do Claude Haiku 4.5 and Yi-Lightning share?

17 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Yi-Lightning has 18.

Related comparisons

Go deeper