Model comparison

Qwen3-4B vs Step 3

Step 3 is the stronger model overall, scoring 40.5 to 31.9 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Qwen3-4B

Alibaba (Qwen)

31.9

Rank #264 Confirmed

Step 3

StepFun

40.5

Rank #149 Confirmed

Summary

The widest gap is in reasoning, where Step 3 leads 28.4 to 19.2.

Side by side

Qwen3-4B and Step 3 specifications
	Qwen3-4B	Step 3
Provider	Alibaba (Qwen)	StepFun
Noometry Index	31.9	40.5
Released	2025-04-29	—
Weights	Open	Open
Context window	—	—
Max output	—	—
Input $ / M tokens	—	—
Output $ / M tokens	—	—
Results tracked	6	17

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

Category by category

Coding Not comparable

Qwen3-4B: —, Step 3: 40.1 (#147)

Coding benchmarks
Benchmark	Qwen3-4B	Step 3
LMArena Coding	—	1367

Agentic & Tool Use Not comparable

Qwen3-4B: 27.6 (#100), Step 3: —

Agentic & Tool Use benchmarks
Benchmark	Qwen3-4B	Step 3
Berkeley Function Calling Leaderboard	35.7%	—

Reasoning Step 3 leads

Qwen3-4B: 19.2 (#268), Step 3: 28.4 (#105)

Reasoning benchmarks
Benchmark	Qwen3-4B	Step 3
Kagi LLM Benchmark	—	62.3%
Chess Puzzles	4%	—
LMArena Hard Prompts	—	1355

Math Step 3 leads

Qwen3-4B: 29.7 (#240), Step 3: 37.6 (#148)

Math benchmarks
Benchmark	Qwen3-4B	Step 3
MathArena Final-Answer Competitions	38.5%	—
OTIS Mock AIME 2024-2025	52.2%	—
LMArena Math	—	1366

Knowledge Step 3 leads

Qwen3-4B: 33.0 (#208), Step 3: 36.8 (#164)

Knowledge benchmarks
Benchmark	Qwen3-4B	Step 3
GPQA Diamond	52.3%	—
Vectara Hallucination Rate	5.7%	—
LMArena Expert	—	1333

Multimodal Not comparable

Qwen3-4B: —, Step 3: 35.5 (#86)

Multimodal benchmarks
Benchmark	Qwen3-4B	Step 3
LMArena Vision	—	1177

Multilingual Not comparable

Qwen3-4B: —, Step 3: 46.3 (#159)

Multilingual benchmarks
Benchmark	Qwen3-4B	Step 3
LMArena Non-English	—	1327
LMArena Chinese	—	1397
LMArena German	—	1371
LMArena Korean	—	1269
LMArena Russian	—	1331
LMArena Spanish	—	1371

Instruction Following Not comparable

Qwen3-4B: —, Step 3: 70.4 (#164)

Instruction Following benchmarks
Benchmark	Qwen3-4B	Step 3
LMArena Instruction Following	—	1332

Long Context Not comparable

Qwen3-4B: —, Step 3: 40.3 (#157)

Long Context benchmarks
Benchmark	Qwen3-4B	Step 3
LMArena Longer Query	—	1326

Writing & Preference Not comparable

Qwen3-4B: —, Step 3: 54.3 (#151)

Writing & Preference benchmarks
Benchmark	Qwen3-4B	Step 3
LMArena Text	—	1350
LMArena Creative Writing	—	1321
LMArena Multi-Turn	—	1341

Frequently asked questions

Is Qwen3-4B better than Step 3?