Skip to content

Qwen3.6 27B

ModelOpen sourceActive
by Alibaba (Qwen) · family “qwen3b”

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs... (description from the OpenRouter listing)

in: textin: imagein: videoout: textReasoningTool useStructured output
Epoch Capabilities Index
146.5 #68 of 268
90% CI 144.1 – 147.8
Listing ↗
Released
22 Apr 2026
Context window
262K tokens
Max output
82K tokens
Input $ / 1M tokens
$0.32
Output $ / 1M tokens
$3.20
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (7)

BenchmarkDomainScorevs best recordedSettingRunSource
LMCAagents34.5%
51%
——External ↗
DTBenchreasoning78.1%
79%
——External ↗
Mystery Game Puzzlesgames7.0% ±2.6
8%
none27 Aug 2026Epoch ↗
FrontierMath-Tiers-1-3-v2-Privatemath35.1% ±2.8
37%
—28 Aug 2026Eval log ↗
Chess Puzzlesgames22.0% ±4.2
31%
—7 Aug 2026Eval log ↗
OTIS Mock AIME 2024-2025math91.1% ±4.3
91%
—7 Aug 2026Eval log ↗
GPQA diamondscience85.9% ±2.5
90%
—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

6 recorded prices on 4 May 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.

Events