Skip to content

Qwen3.5 Plus 2026-02-15

ModelActive
by Alibaba (Qwen) · family “qwen3-plus”

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of... (description from the OpenRouter listing)

in: textin: imagein: videoout: textReasoningTool useStructured output
Epoch Capabilities Index
Not scored by Epoch AI
Listing ↗
Released
16 Feb 2026
Context window
1M tokens
Max output
66K tokens
Input $ / 1M tokens
$0.26
Output $ / 1M tokens
$1.56
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (11)

BenchmarkDomainScorevs best recordedSettingRunSource
LMCAagents36.4%
53%
——External ↗
DTBenchreasoning80.5%
81%
——External ↗
Mystery Game Puzzlesgames17.0% ±3.8
20%
none27 Aug 2026Epoch ↗
CL-bench Lifelong-context12.4%
56%
——External ↗
CL-benchlong-context19.8%
71%
——External ↗
Chess Puzzlesgames22.0% ±4.2
31%
—7 Aug 2026Eval log ↗
SimpleQA Verifiedknowledge25.4% ±1.4
34%
—27 Aug 2026Eval log ↗
FrontierMath-Tier-4-2025-07-01-Privatesupersededmath2.1% ±2.1
4%
—15 May 2026Epoch ↗
FrontierMath-2025-02-28-Privatesupersededmath21.0% ±2.4
40%
—14 May 2026Epoch ↗
OTIS Mock AIME 2024-2025math86.7% ±5.1
87%
—7 Aug 2026Eval log ↗
GPQA diamondscience84.8% ±2.6
89%
—7 Aug 2026Eval log ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

8 recorded prices on 3 Mar 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 10h ago. Steps show when the price changed.

Events