Back

Alibaba

Qwen3.6 Plus

ReasoningClosed weightsModels.dev
Intelligence
27.0
Rank 152 of 744 measured models
Coding
54.5
Rank 107 of 298 measured models
Output speed
55.9 t/s
Rank 299 of 403 measured models
Price/1M
$1.13
Rank 392 of 659 measured models
Context window
1M
Rank 84 of 1199 measured models

Qwen3.6 Plus scores 27.0 on the Artificial Analysis Intelligence Index, ranking 152nd of 744 measured models. The closest models on this index are Grok Build 0.1 0616 (27.2), Kimi K2.6 (27.0), and Agnes 2.5 Pro Alpha (based on Qwen3.5 397B A17B) (26.8). At $1.13 per million tokens (3:1 input/output blended price), it is cheaper than Grok Build 0.1 0616 ($1.25) and Kimi K2.6 ($1.71), more expensive than Agnes 2.5 Pro Alpha (based on Qwen3.5 397B A17B) ($0.563). With an output speed of 55.9 t/s, it is faster than Kimi K2.6 (52.8 t/s), slower than Grok Build 0.1 0616 (67.4 t/s) and Agnes 2.5 Pro Alpha (based on Qwen3.5 397B A17B) (160 t/s).

Artificial Analysis Indices
Intelligence27.0
Rank 152 of 744 measured models
Coding54.5
Rank 107 of 298 measured models
Standard Benchmarks
GPQA Diamond88.2%
Rank 95 of 619 measured models
HLE27.8%
Rank 172 of 664 measured models
IFBench75.2%
Rank 35 of 450 measured models
AA-LCR78.3%
Rank 111 of 575 measured models
TerminalBench Hard43.9%
Rank 37 of 432 measured models
Terminal-Bench 2.161.4%
Rank 99 of 244 measured models
τ²-Bench97.7%
Rank 9 of 440 measured models
τ-Bench Banking20.8%
Rank 98 of 211 measured models
Additional benchmarks8
Design Arena · 3d50.6%
Design Arena · Asciiart41.2%
Design Arena · Codecategories50.3%
Design Arena · Dataviz50.8%
Design Arena · Gamedev48.6%
Design Arena · Svg50.4%
Design Arena · Uicomponent50.6%
Design Arena · Website50.2%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy