Benchmark suiteUpdated May 27, 2026

Qwen3 VL 235b A22B Thinking.

A model-level benchmark profile for Qwen3 VL 235b A22B Thinking, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

Alibaba lab page

Lab

Alibaba

Open weights

Coverage

44%

4 of 9 tracked signals

Best Arena rank

#58

Vision Arena

Best suite

#21

Agents / 97

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

Qwen3 VL 235b A22B Thinking is strongest on agents.

44% coverage

Its best composite result is rank #21 in the agents view, with a 97 agent proxy. The strongest raw Arena signal is Vision Arena at rank #58 with 2,370 public votes.

Best current lane

Agents

#21 / 97 agent proxy

Strongest raw signal

Vision

#58, 1190 score

Commercial posture

$2.17

5.14s first token / 36 tok/s

Coverage gaps

Text ArenaWebDev ArenaSearch ArenaDocument ArenaSWE-bench

Profile completeness

4 of 9 signals matched

44%

Arena categories

1/5

Vision

Commercial match

Live

Qwen3 VL 235B A22B (Reasoning)

SWE-bench

Not listed

No confident software benchmark row

Raw identifier

qwen3-vl-235b-a22b-thinking

ReasoningOpen weights

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

WebDev Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Vision Arena

Arena category

1,190#58

1177-1202 CI

2,370 votes

May 18, 2026

Arena public leaderboard dataset

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

Not listed

No confident SWE-bench row matched to this model.

Coverage gap

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$2.17

USD / 1M tokens

Input price

$0.840

USD / 1M input tokens

Output price

$6.18

USD / 1M output tokens

Latency

5.14s

Median time to first token

Output speed

36 tok/s

Median generation speed

Matched source row

Qwen3 VL 235B A22B (Reasoning)

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#4261

value index

blended / 1M tokens$2.17

time to first token5.14s

output speed36 tok/s

Coding

Code Arena, SWE-bench, and output speed

#982

coding index

Code ArenaNot listed