Noometry

Model comparison

Qwen3-Next 80B-A3B Instruct vs Step 3

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Qwen3-Next 80B-A3B Instruct Alibaba (Qwen)

43.0

Rank #102 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Qwen3-Next 80B-A3B Instruct scores higher in 7 categories and Step 3 in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Qwen3-Next 80B-A3B Instruct leads 52.1 to 46.3.

Side by side

Qwen3-Next 80B-A3B InstructStep 3
ProviderAlibaba (Qwen)StepFun
Noometry Index43.040.5
Released2025-09—
WeightsOpenOpen
Context window131K—
Max output33K—
Input $ / M tokens$0.50—
Output $ / M tokens$2—
Results tracked2517

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

Category by category

Coding Qwen3-Next 80B-A3B Instruct leads

Qwen3-Next 80B-A3B Instruct: 42.5 (#98), Step 3: 40.1 (#147)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Coding14401367

Reasoning Qwen3-Next 80B-A3B Instruct leads

Qwen3-Next 80B-A3B Instruct: 31.1 (#81), Step 3: 28.4 (#105)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
Kagi LLM Benchmark66.7%62.3%
LMArena Hard Prompts14281355

Math Qwen3-Next 80B-A3B Instruct leads

Qwen3-Next 80B-A3B Instruct: 38.8 (#126), Step 3: 37.6 (#148)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Math14401366
Omni-MATH46.7%—

Knowledge Qwen3-Next 80B-A3B Instruct leads

Qwen3-Next 80B-A3B Instruct: 41.8 (#106), Step 3: 36.8 (#164)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Expert14171333
MMLU-Pro78.6%—
Vectara Hallucination Rate9.3%—
GPQA (HELM)63%—

Multimodal Not comparable

Qwen3-Next 80B-A3B Instruct: —, Step 3: 35.5 (#86)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Vision—1177

Multilingual Qwen3-Next 80B-A3B Instruct leads

Qwen3-Next 80B-A3B Instruct: 52.1 (#93), Step 3: 46.3 (#159)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Non-English14071327
LMArena Chinese14601397
LMArena German14171371
LMArena Korean13641269
LMArena Russian14041331
LMArena Spanish14351371
LMArena French1413—
LMArena Japanese1395—

Instruction Following Too close to call

Qwen3-Next 80B-A3B Instruct: 70.8 (#159), Step 3: 70.4 (#164)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Instruction Following13891332
IFEval81%—

Long Context Step 3 leads

Qwen3-Next 80B-A3B Instruct: 37.0 (#223), Step 3: 40.3 (#157)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Longer Query14031326
Fiction.LiveBench55.6%—

Writing & Preference Qwen3-Next 80B-A3B Instruct leads

Qwen3-Next 80B-A3B Instruct: 58.0 (#121), Step 3: 54.3 (#151)

BenchmarkQwen3-Next 80B-A3B InstructStep 3
LMArena Text14171350
LMArena Creative Writing13341321
LMArena Multi-Turn14161341
WildBench80.7%—

Frequently asked questions

Is Qwen3-Next 80B-A3B Instruct better than Step 3?

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 40.5 on the Noometry Index.

Is Qwen3-Next 80B-A3B Instruct or Step 3 better for coding?

Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 40.1 in the Noometry coding category.

How many benchmarks do Qwen3-Next 80B-A3B Instruct and Step 3 share?

16 benchmarks have published results for both models. Qwen3-Next 80B-A3B Instruct has 25 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper