Qwen3.6-Max-Preview

Qwen·Pending·Released 2026-04-18text
Context256k
Max output-
Input / 1M$1.3 ↗
Output / 1M$7.8 ↗
Cached in-
Benchmarks17

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

Chess Puzzles (Epoch AI run)#55/9220% ↗
Mystery Game Puzzles (Epoch AI run)#41/6819% ↗
Vending-Bench 2 (Andon Labs)#33/594254.19 ↗
LMArena Elo#42/1411460.3 ↗
SimpleBench (SimpleBench)#25/7363% ↗
NL2Repo#6/642.9% ↗
QwenClawBench59% ↗
SciCode#3/647% ↗
SkillsBench#1/255.6% ↗
SuperGPQA#1/1773.9% ↗
Terminal-Bench 2.0 (Terminus-2)65.4% ↗

Qwen3.6-Max-Preview FAQ

What is Qwen3.6-Max-Preview?
Qwen3.6-Max-Preview is a large language model from Qwen, released on April 18, 2026. It accepts text input.
When was Qwen3.6-Max-Preview released?
Qwen released Qwen3.6-Max-Preview on April 18, 2026.
How much does Qwen3.6-Max-Preview cost?
Qwen3.6-Max-Preview costs $1.30 per 1M input tokens and $7.80 per 1M output tokens through the Qwen API. Prices are from Qwen's official pricing as of October 5, 2026.
What is Qwen3.6-Max-Preview's context window?
Qwen3.6-Max-Preview has a 256K-token context window.
How does Qwen3.6-Max-Preview score on benchmarks?
Qwen3.6-Max-Preview has 17 cited benchmark scores, including Chess Puzzles (Epoch AI run) 20%, GPQA Diamond (Epoch AI run) 87.4% and Mystery Game Puzzles (Epoch AI run) 19%. Each score links to its source.

Access Qwen3.6-Max-Preview and every other model through one endpoint with automatic failover: Respan gateway.