Noometry

Model comparison

Claude 3.5 Haiku vs Yi-Lightning

Yi-Lightning is the stronger model overall, scoring 37.1 to 29.2 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Yi-Lightning 01.AI

37.1

Rank #209 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Yi-Lightning leads 36.2 to 14.7.
  • The biggest single-benchmark swing is Aider Polyglot: 28% for Claude 3.5 Haiku and 12.9% for Yi-Lightning.

Side by side

Claude 3.5 HaikuYi-Lightning
ProviderAnthropic01.AI
Noometry Index29.237.1
Released2024-10-222024-12-02
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4918

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

Category by category

Coding Claude 3.5 Haiku leads

Claude 3.5 Haiku: 32.9 (#265), Yi-Lightning: 27.4 (#320)

BenchmarkClaude 3.5 HaikuYi-Lightning
Aider Polyglot28%12.9%
LMArena Coding12861312
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Yi-Lightning: —

BenchmarkClaude 3.5 HaikuYi-Lightning
BALROG19.3%—

Reasoning Yi-Lightning leads

Claude 3.5 Haiku: 17.7 (#290), Yi-Lightning: 25.9 (#139)

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Hard Prompts12511302
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Yi-Lightning leads

Claude 3.5 Haiku: 14.7 (#300), Yi-Lightning: 36.2 (#172)

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Math12441300
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Yi-Lightning leads

Claude 3.5 Haiku: 18.7 (#281), Yi-Lightning: 35.4 (#185)

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Expert12081286
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Yi-Lightning: —

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Vision1092—
GeoBench34%—

Multilingual Yi-Lightning leads

Claude 3.5 Haiku: 40.0 (#218), Yi-Lightning: 42.2 (#196)

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Non-English12381269
LMArena Chinese12291320
LMArena French12641305
LMArena German12371267
LMArena Japanese11751228
LMArena Korean11731192
LMArena Russian12531255
LMArena Spanish12611315

Instruction Following Yi-Lightning leads

Claude 3.5 Haiku: 62.9 (#234), Yi-Lightning: 67.4 (#196)

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Instruction Following12411278
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Yi-Lightning leads

Claude 3.5 Haiku: 38.3 (#200), Yi-Lightning: 39.4 (#181)

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Longer Query12611297

Writing & Preference Yi-Lightning leads

Claude 3.5 Haiku: 42.7 (#234), Yi-Lightning: 50.2 (#184)

BenchmarkClaude 3.5 HaikuYi-Lightning
LMArena Text12551302
LMArena Creative Writing12331280
LMArena Multi-Turn12651311
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Yi-Lightning?

Yi-Lightning is the stronger model overall, scoring 37.1 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Yi-Lightning better for coding?

Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 27.4 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Yi-Lightning share?

18 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Yi-Lightning has 18.

Related comparisons

Go deeper