Back

Alibaba

Qwen3 VL 235B A22B

ReasoningOpen weights
Intelligence
13.4
Rank 334 of 744 measured models
Output speed
57.1 t/s
Rank 294 of 403 measured models
Price/1M
$1.30
Rank 412 of 659 measured models
Context window
262K
Rank 458 of 1199 measured models

Qwen3 VL 235B A22B (Reasoning) scores 13.4 on the Artificial Analysis Intelligence Index, ranking 334th of 744 measured models. The closest models on this index are Apriel-v1.6-15B-Thinker (13.4), Nova 2 Lite (13.4), and Qwen3 VL 235B A22B Thinking (13.4). At $1.30 per million tokens (3:1 input/output blended price), it is priced close to Qwen3 VL 235B A22B Thinking ($1.30), more expensive than Nova 2 Lite ($0.85).

Artificial Analysis Indices
Reasoning
Intelligence13.4
Rank 334 of 744 measured models
Math88.3
Rank 35 of 270 measured models
Standard Benchmarks
MMLU Pro83.6%
Rank 52 of 349 measured models
GPQA Diamond77.2%
Rank 238 of 619 measured models
HLE11.9%
Rank 297 of 664 measured models
LiveCodeBench64.6%
Rank 99 of 343 measured models
AIME 202588.3%
Rank 35 of 270 measured models
IFBench56.5%
Rank 147 of 450 measured models
AA-LCR63.7%
Rank 268 of 575 measured models
TerminalBench Hard11.4%
Rank 228 of 432 measured models
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