Model comparison

Qwen3.5 Plus vs Step 3

Qwen3.5 Plus is the stronger model overall, scoring 42.9 to 40.5 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Qwen3.5 Plus

Alibaba (Qwen)

42.9

Rank #106 Confirmed

Step 3

StepFun

40.5

Rank #149 Confirmed

Summary

The widest gap is in math, where Qwen3.5 Plus leads 49.6 to 37.6.
Step 3 has downloadable open weights; the other is API-only.

Side by side

Qwen3.5 Plus and Step 3 specifications
	Qwen3.5 Plus	Step 3
Provider	Alibaba (Qwen)	StepFun
Noometry Index	42.9	40.5
Released	2026-02-16	—
Weights	Proprietary	Open
Context window	1M	—
Max output	66K	—
Input $ / M tokens	$0.40	—
Output $ / M tokens	$2.40	—
Results tracked	15	17

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

Category by category

Coding Not comparable

Qwen3.5 Plus: —, Step 3: 40.1 (#147)

Coding benchmarks
Benchmark	Qwen3.5 Plus	Step 3
LMArena Coding	—	1367
ALE-Bench	621.92	—

Agentic & Tool Use Not comparable

Qwen3.5 Plus: —, Step 3: —

Agentic & Tool Use benchmarks
Benchmark	Qwen3.5 Plus	Step 3
Vending-Bench 2	0.54	—

Reasoning Qwen3.5 Plus leads

Qwen3.5 Plus: 32.8 (#74), Step 3: 28.4 (#105)

Reasoning benchmarks
Benchmark	Qwen3.5 Plus	Step 3
Kagi LLM Benchmark	—	62.3%
Chess Puzzles	22%	—
LMArena Hard Prompts	—	1355
Mystery Game Puzzles	17%	—
DTBench	80.5%	—
LMCA	36.4%	—
Epoch Capabilities Index	146.78	—

Math Qwen3.5 Plus leads

Qwen3.5 Plus: 49.6 (#61), Step 3: 37.6 (#148)

Math benchmarks
Benchmark	Qwen3.5 Plus	Step 3
OTIS Mock AIME 2024-2025	86.7%	—
LMArena Math	—	1366
FrontierMath (Feb 2025 set)	21%	—
FrontierMath Tier 4 (v1)	2.1%	—

Knowledge Qwen3.5 Plus leads

Qwen3.5 Plus: 46.0 (#83), Step 3: 36.8 (#164)

Knowledge benchmarks
Benchmark	Qwen3.5 Plus	Step 3
GPQA Diamond	84.8%	—
SimpleQA Verified	25.4%	—
Vectara Hallucination Rate	10.7%	—
LMArena Expert	—	1333

Multimodal Not comparable

Qwen3.5 Plus: —, Step 3: 35.5 (#86)

Multimodal benchmarks
Benchmark	Qwen3.5 Plus	Step 3
LMArena Vision	—	1177

Multilingual Not comparable

Qwen3.5 Plus: —, Step 3: 46.3 (#159)

Multilingual benchmarks
Benchmark	Qwen3.5 Plus	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

Qwen3.5 Plus: —, Step 3: 70.4 (#164)

Instruction Following benchmarks
Benchmark	Qwen3.5 Plus	Step 3
LMArena Instruction Following	—	1332

Long Context Qwen3.5 Plus leads

Qwen3.5 Plus: 43.0 (#113), Step 3: 40.3 (#157)

Long Context benchmarks
Benchmark	Qwen3.5 Plus	Step 3
CL-bench	19.8%	—
CL-bench Life	12.4%	—
LMArena Longer Query	—	1326

Writing & Preference Not comparable

Qwen3.5 Plus: —, Step 3: 54.3 (#151)

Writing & Preference benchmarks
Benchmark	Qwen3.5 Plus	Step 3
LMArena Text	—	1350
LMArena Creative Writing	—	1321
LMArena Multi-Turn	—	1341

Frequently asked questions

Is Qwen3.5 Plus better than Step 3?