Noometry

Model comparison

Qwen3 32B vs Yi-Lightning

Qwen3 32B is the stronger model overall, scoring 38.8 to 36.5 on the Noometry Index.

Last verified . 14 shared benchmarks.

Qwen3 32B Alibaba (Qwen)

38.8

Rank #166 Confirmed

Yi-Lightning 01.AI

36.5

Rank #206 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Qwen3 32B 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 Qwen3 32B leads 37.3 to 27.0.
  • The biggest single-benchmark swing is Aider Polyglot: 40% for Qwen3 32B and 12.9% for Yi-Lightning.
  • Qwen3 32B has downloadable open weights; the other is API-only.

Side by side

Qwen3 32BYi-Lightning
ProviderAlibaba (Qwen)01.AI
Noometry Index38.836.5
Released2025-042024-12-02
WeightsOpenProprietary
Context window131K—
Max output16K—
Input $ / M tokens$0.70—
Output $ / M tokens$2.80—
Results tracked2618

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

Category by category

Coding Qwen3 32B leads

Qwen3 32B: 37.3 (#184), Yi-Lightning: 27.0 (#315)

BenchmarkQwen3 32BYi-Lightning
Aider Polyglot40%12.9%
LMArena Coding13581313
SciCode35.4%—

Agentic & Tool Use Not comparable

Qwen3 32B: 32.3 (#58), Yi-Lightning: —

BenchmarkQwen3 32BYi-Lightning
Berkeley Function Calling Leaderboard48.7%—

Reasoning Yi-Lightning leads

Qwen3 32B: 19.6 (#233), Yi-Lightning: 24.9 (#137)

BenchmarkQwen3 32BYi-Lightning
LMArena Hard Prompts13351302
Kagi LLM Benchmark54.9%—
CritPt0.3%—
Chess Puzzles5%—
DTBench67.5%—
LMCA17.3%—
Epoch Capabilities Index138.51—

Math Qwen3 32B leads

Qwen3 32B: 37.9 (#89), Yi-Lightning: 33.5 (#173)

BenchmarkQwen3 32BYi-Lightning
LMArena Math13991300
OTIS Mock AIME 2024-202566.9%—

Knowledge Qwen3 32B leads

Qwen3 32B: 40.0 (#112), Yi-Lightning: 34.8 (#182)

BenchmarkQwen3 32BYi-Lightning
LMArena Expert13621286
GPQA Diamond65.7%—
Vectara Hallucination Rate5.9%—

Multilingual Qwen3 32B leads

Qwen3 32B: 45.8 (#162), Yi-Lightning: 42.4 (#191)

BenchmarkQwen3 32BYi-Lightning
LMArena Non-English13171269
LMArena Chinese13571320
LMArena German13411267
LMArena Russian13111255
LMArena French—1304
LMArena Japanese—1228
LMArena Korean—1192
LMArena Spanish—1315

Instruction Following Qwen3 32B leads

Qwen3 32B: 69.1 (#174), Yi-Lightning: 67.6 (#191)

BenchmarkQwen3 32BYi-Lightning
LMArena Instruction Following13051278

Long Context Qwen3 32B leads

Qwen3 32B: 43.7 (#83), Yi-Lightning: 39.4 (#176)

BenchmarkQwen3 32BYi-Lightning
LMArena Longer Query13271297
Fiction.LiveBench74.2%—

Writing & Preference Qwen3 32B leads

Qwen3 32B: 53.1 (#158), Yi-Lightning: 50.4 (#178)

BenchmarkQwen3 32BYi-Lightning
LMArena Text13401302
LMArena Creative Writing12971280
LMArena Multi-Turn13311311

Frequently asked questions

Is Qwen3 32B better than Yi-Lightning?

Qwen3 32B is the stronger model overall, scoring 38.8 to 36.5 on the Noometry Index.

Is Qwen3 32B or Yi-Lightning better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.3 versus 27.0 in the Noometry coding category.

How many benchmarks do Qwen3 32B and Yi-Lightning share?

14 benchmarks have published results for both models. Qwen3 32B has 26 scored results on Noometry and Yi-Lightning has 18.

Related comparisons

Go deeper