Model

Qwen3.5-Plus

CLOSED

Alibaba · Qwen3.5 family · released Feb 16, 2026

Hosted/API counterpart to the open-weight Qwen3.5-397B-A17B, launched the same day via Alibaba Cloud Model Studio with a 1M-token default context, official built-in tools, and adaptive tool use on top of the open-weight base.

ReasoningCodingVisionFunction callingTool useAgentic

1882.6

Elo · rank #68

Parameters

Undisclosed

Active params

Undisclosed

Context

1M tokens

Architecture

Hosted product tier of the Qwen3.5 hybrid-attention MoE line (Gated DeltaNet + Gated Attention + MoE, Qwen3-Next lineage); exact parameter/expert configuration for the specific hosted 'Plus' checkpoint undisclosed

License

Proprietary

Languages

—

API price (in/out)

$0.4 / $2.4

Modalities

text · vision

Benchmark results

Bar shows position within the tracked field; marker = field best

C-EvalKnowledge92.3%#3

best: Qwen3.6-Plus · 93.3%

GPQA DiamondReasoning85.9%#54

best: GPT-5.6 · 94.6%

IFBenchReasoning51.1%#36

best: MiniMax M3 · 83.0%

IFEvalReasoning89.7%#20

best: Gemma 4 26B A4B · 98.5%

LiveCodeBenchCoding67.1%#77

best: DeepSeek-V4-Pro (Think Max) · 93.5%

MMLU-ProKnowledge86.8%#17

best: Claude Fable 5 · 91.5%

MMLU-ReduxKnowledge94.3%#6

best: Qwen3.7-Max · 95.0%

MMMU-ProVision22.8%#52

best: Claude Opus 4.7 · 85.5%

MMMUVision81.0%#21

best: Claude Fable 5 · 89.3%

SuperGPQAReasoning67.4%#6

best: Qwen3.7-Max · 73.6%

SWE-bench VerifiedCoding71.2%#56

best: Claude Fable 5 · 95.0%

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

$0.4

Output / M tok

$2.4

Qwen3.5 family

Elo progression across releases

Qwen3.5-397B-A17BFeb 20262182.0 Qwen3.5-PlusFeb 20261882.6 Qwen3.5-122B-A10BFeb 20262021.4 Qwen3.5-Omni-FlashMar 20261471.5 Qwen3.5-Omni-PlusMar 20261834.0

Resources

DOCShttps://qwen.ai/blog?id=qwen3.5 APIAvailable via Alibaba API

API price $0.4/$2.4 · each benchmark row carries its own source badge (see methodology)