Model profile · Qwen

qwen3-vl-235b-a22b-thinking

Open weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 1.4%
Verified coverage: 1.4%
Spread: 19.9%
Last verified: Oct 3, 2026

51%capability fit

textcodevision1 aliases35 official source links

Open compare

Data version

Current snapshot.

Published Oct 3, 2026Model list checked4 stale sources105 claim warnings9 providers · 1334 tracked models

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance. View live data status.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set. Capability summaries exclude archived categories, speed, and cost; those rows remain below.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text18 benchmarks60.9%

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #148

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 60.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: overall. Source rank: #165. Votes: 7805. Organization: alibaba. License: Apache 2.0.

60.9% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,388 - 1,402

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #168

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,340
Percentile: 55.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: creative_writing. Source rank: #188. Votes: 1006. Organization: alibaba. License: Apache 2.0.

55.3% percentile inside its fair comparison set

1,340Raw benchmark valueCI 1,322 - 1,358

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #157

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 58.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: english. Source rank: #175. Votes: 3465. Organization: alibaba. License: Apache 2.0.

58.5% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,393 - 1,413

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #151

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 60.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: exclude_ties. Source rank: #168. Votes: 5499. Organization: alibaba. License: Apache 2.0.

60.1% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,362 - 1,382

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #149

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: hard_prompts. Source rank: #166. Votes: 4014. Organization: alibaba. License: Apache 2.0.

60.6% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,408 - 1,426

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #160

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 57.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: hard_prompts_english. Source rank: #179. Votes: 1813. Organization: alibaba. License: Apache 2.0.

57.5% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,404 - 1,432

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #149

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: instruction_following. Source rank: #168. Votes: 2137. Organization: alibaba. License: Apache 2.0.

60.6% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,370 - 1,394

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #144

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 59.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: longer_query. Source rank: #163. Votes: 1758. Organization: alibaba. License: Apache 2.0.

59.7% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,390 - 1,418

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #164

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: multi_turn. Source rank: #183. Votes: 1260. Organization: alibaba. License: Apache 2.0.

56.4% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,368 - 1,401

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #135

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: overall. Source rank: #149. Votes: 7805. Organization: alibaba. License: Apache 2.0.

64.4% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,394 - 1,408

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #150

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 60.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: creative_writing. Source rank: #169. Votes: 1006. Organization: alibaba. License: Apache 2.0.

60.2% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,328 - 1,365

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #123

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 67.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: english. Source rank: #133. Votes: 3465. Organization: alibaba. License: Apache 2.0.

67.6% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,410 - 1,430

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #137

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 63.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: exclude_ties. Source rank: #152. Votes: 5499. Organization: alibaba. License: Apache 2.0.

63.8% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,370 - 1,389

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #138

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 63.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: hard_prompts. Source rank: #151. Votes: 4014. Organization: alibaba. License: Apache 2.0.

63.6% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,397 - 1,416

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #133

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 64.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: hard_prompts_english. Source rank: #146. Votes: 1813. Organization: alibaba. License: Apache 2.0.

64.7% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,402 - 1,430

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #146

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 61.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: instruction_following. Source rank: #162. Votes: 2137. Organization: alibaba. License: Apache 2.0.

61.4% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,362 - 1,387

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #142

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: longer_query. Source rank: #159. Votes: 1758. Organization: alibaba. License: Apache 2.0.

60.3% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,377 - 1,405

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #150

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 60.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: multi_turn. Source rank: #167. Votes: 1260. Organization: alibaba. License: Apache 2.0.

60.2% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,370 - 1,404

Coding2 benchmarksn/a

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #138

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: coding. Source rank: #153. Votes: 1628. Organization: alibaba. License: Apache 2.0.

63.1% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,437 - 1,466

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #127

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 66%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: coding. Source rank: #139. Votes: 1628. Organization: alibaba. License: Apache 2.0.

66% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,410 - 1,439

Reasoning / math / science2 benchmarksn/a

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #139

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 61.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: math. Source rank: #157. Votes: 419. Organization: alibaba. License: Apache 2.0.

61.6% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,372 - 1,429

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: math. Source rank: #137. Votes: 419. Organization: alibaba. License: Apache 2.0.

65.2% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,382 - 1,439

Professional reasoning18 benchmarksn/a

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: expert. Source rank: #131. Votes: 398. Organization: alibaba. License: Apache 2.0.

64.2% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,409 - 1,468

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #151

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 59.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_business_and_management_and_financial_operations. Source rank: #168. Votes: 1565. Organization: alibaba. License: Apache 2.0.

59.3% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,378 - 1,407

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #144

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,362
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_entertainment_and_sports_and_media. Source rank: #163. Votes: 1434. Organization: alibaba. License: Apache 2.0.

61.8% percentile inside its fair comparison set

1,362Raw benchmark valueCI 1,347 - 1,377

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #144

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 59%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_legal_and_government. Source rank: #162. Votes: 491. Organization: alibaba. License: Apache 2.0.

59% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,377 - 1,429

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #153

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 59.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_life_and_physical_and_social_science. Source rank: #171. Votes: 1235. Organization: alibaba. License: Apache 2.0.

59.4% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,391 - 1,424

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #111

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_mathematical. Source rank: #121. Votes: 377. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,401 - 1,459

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #148

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 57.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_medicine_and_healthcare. Source rank: #166. Votes: 437. Organization: alibaba. License: Apache 2.0.

57.5% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,388 - 1,444

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #144

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_software_and_it_services. Source rank: #159. Votes: 2767. Organization: alibaba. License: Apache 2.0.

62% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,424 - 1,446

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #155

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 58.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_writing_and_literature_and_language. Source rank: #175. Votes: 1736. Organization: alibaba. License: Apache 2.0.

58.9% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,352 - 1,380

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #110

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: expert. Source rank: #118. Votes: 398. Organization: alibaba. License: Apache 2.0.

66.7% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,397 - 1,456

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #137

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_business_and_management_and_financial_operations. Source rank: #150. Votes: 1565. Organization: alibaba. License: Apache 2.0.

63.1% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,376 - 1,405

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 66.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_entertainment_and_sports_and_media. Source rank: #139. Votes: 1434. Organization: alibaba. License: Apache 2.0.

66.6% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,355 - 1,386

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #134

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 61.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_legal_and_government. Source rank: #148. Votes: 491. Organization: alibaba. License: Apache 2.0.

61.9% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,381 - 1,431

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #139

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_life_and_physical_and_social_science. Source rank: #152. Votes: 1235. Organization: alibaba. License: Apache 2.0.

63.1% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,395 - 1,429

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #91

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 74.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_mathematical. Source rank: #95. Votes: 377. Organization: alibaba. License: Apache 2.0.

74.7% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,408 - 1,466

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #121

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 65.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_medicine_and_healthcare. Source rank: #132. Votes: 437. Organization: alibaba. License: Apache 2.0.

65.3% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,388 - 1,444

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #131

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 65.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_software_and_it_services. Source rank: #143. Votes: 2767. Organization: alibaba. License: Apache 2.0.

65.4% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,414 - 1,435

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #145

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 61.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: industry_writing_and_literature_and_language. Source rank: #163. Votes: 1736. Organization: alibaba. License: Apache 2.0.

61.6% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,352 - 1,380

Vision understanding14 benchmarks41%

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #83

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 41%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: overall. Source rank: #94. Votes: 2388. Organization: alibaba. License: Apache 2.0.

41% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,176 - 1,200

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #69

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,180
Percentile: 17.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: creative_writing_vision. Source rank: #78. Votes: 178. Organization: alibaba. License: Apache 2.0.

17.1% percentile inside its fair comparison set

1,180Raw benchmark valueCI 1,136 - 1,224

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #78

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,211
Percentile: 22.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: diagram. Source rank: #88. Votes: 464. Organization: alibaba. License: Apache 2.0.

22.2% percentile inside its fair comparison set

1,211Raw benchmark valueCI 1,184 - 1,237

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #80

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,193
Percentile: 42.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: english. Source rank: #90. Votes: 972. Organization: alibaba. License: Apache 2.0.

42.8% percentile inside its fair comparison set

1,193Raw benchmark valueCI 1,175 - 1,212

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #73

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,226
Percentile: 25%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: homework. Source rank: #84. Votes: 298. Organization: alibaba. License: Apache 2.0.

25% percentile inside its fair comparison set

1,226Raw benchmark valueCI 1,193 - 1,258

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #80

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,200
Percentile: 21%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: ocr. Source rank: #89. Votes: 1322. Organization: alibaba. License: Apache 2.0.

21% percentile inside its fair comparison set

1,200Raw benchmark valueCI 1,184 - 1,216

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #74

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,206
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: overall. Source rank: #84. Votes: 2388. Organization: alibaba. License: Apache 2.0.

47.5% percentile inside its fair comparison set

1,206Raw benchmark valueCI 1,194 - 1,218

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #69

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,196
Percentile: 17.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: creative_writing_vision. Source rank: #78. Votes: 178. Organization: alibaba. License: Apache 2.0.

17.1% percentile inside its fair comparison set

1,196Raw benchmark valueCI 1,152 - 1,240

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #72

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,214
Percentile: 28.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: diagram. Source rank: #82. Votes: 464. Organization: alibaba. License: Apache 2.0.

28.3% percentile inside its fair comparison set

1,214Raw benchmark valueCI 1,187 - 1,240

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #73

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,215
Percentile: 47.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: english. Source rank: #84. Votes: 972. Organization: alibaba. License: Apache 2.0.

47.8% percentile inside its fair comparison set

1,215Raw benchmark valueCI 1,197 - 1,234

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,234
Percentile: 28.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: homework. Source rank: #79. Votes: 298. Organization: alibaba. License: Apache 2.0.

28.1% percentile inside its fair comparison set

1,234Raw benchmark valueCI 1,202 - 1,266

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #73

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,212
Percentile: 28%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: ocr. Source rank: #83. Votes: 1322. Organization: alibaba. License: Apache 2.0.

28% percentile inside its fair comparison set

1,212Raw benchmark valueCI 1,196 - 1,228

Vision Arena · Creative Writing

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,218
Percentile: 62.5%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: creative_writing. Source rank: #14. Votes: 219. Organization: alibaba. License: Apache 2.0.

62.5% percentile inside its fair comparison set

1,218Raw benchmark valueCI 1,179 - 1,256

Vision Arena · Creative Writing · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #12

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,230
Percentile: 65.6%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: creative_writing. Source rank: #13. Votes: 219. Organization: alibaba. License: Apache 2.0.

65.6% percentile inside its fair comparison set

1,230Raw benchmark valueCI 1,192 - 1,268

Multilingual16 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #149

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 58%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: chinese. Source rank: #166. Votes: 437. Organization: alibaba. License: Apache 2.0.

58% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,395 - 1,451

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #94

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 65.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: german. Source rank: #109. Votes: 179. Organization: alibaba. License: Apache 2.0.

65.8% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,372 - 1,459

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #114

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,353
Percentile: 53.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: korean. Source rank: #130. Votes: 222. Organization: alibaba. License: Apache 2.0.

53.7% percentile inside its fair comparison set

1,353Raw benchmark valueCI 1,313 - 1,393

Text Arena · Non English

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #145

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 61.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: non_english. Source rank: #163. Votes: 4340. Organization: alibaba. License: Apache 2.0.

61.7% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,372 - 1,389

Text Arena · Polish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #137

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 31.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: polish. Source rank: #160. Votes: 397. Organization: alibaba. License: Apache 2.0.

31.7% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,338 - 1,394

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #148

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 56.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: russian. Source rank: #166. Votes: 611. Organization: alibaba. License: Apache 2.0.

56.9% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,363 - 1,408

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #124

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 52.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: spanish. Source rank: #140. Votes: 377. Organization: alibaba. License: Apache 2.0.

52.5% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,371 - 1,433

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #128

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 63.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: chinese. Source rank: #139. Votes: 437. Organization: alibaba. License: Apache 2.0.

63.9% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,413 - 1,469

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #86

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: german. Source rank: #98. Votes: 179. Organization: alibaba. License: Apache 2.0.

68.8% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,373 - 1,460

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #114

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 53.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: korean. Source rank: #128. Votes: 222. Organization: alibaba. License: Apache 2.0.

53.7% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,314 - 1,394

Text Arena · Non English · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #146

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 61.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: non_english. Source rank: #162. Votes: 4340. Organization: alibaba. License: Apache 2.0.

61.4% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,369 - 1,386

Text Arena · Polish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,367
Percentile: 35.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: polish. Source rank: #148. Votes: 397. Organization: alibaba. License: Apache 2.0.

35.2% percentile inside its fair comparison set

1,367Raw benchmark valueCI 1,339 - 1,395

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #154

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,369
Percentile: 55.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: russian. Source rank: #172. Votes: 611. Organization: alibaba. License: Apache 2.0.

55.1% percentile inside its fair comparison set

1,369Raw benchmark valueCI 1,347 - 1,392

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #125

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 52.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: spanish. Source rank: #138. Votes: 377. Organization: alibaba. License: Apache 2.0.

52.1% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,371 - 1,433

Vision Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #76

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,186
Percentile: 27.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: chinese. Source rank: #87. Votes: 160. Organization: alibaba. License: Apache 2.0.

27.9% percentile inside its fair comparison set

1,186Raw benchmark valueCI 1,142 - 1,230

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,221
Percentile: 33.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-vl-235b-a22b-thinking`. Category: chinese. Source rank: #80. Votes: 160. Organization: alibaba. License: Apache 2.0.

33.7% percentile inside its fair comparison set

1,221Raw benchmark valueCI 1,177 - 1,264

Source links and registry checks

official

Arena

Oct 3, 2026

qwen3-vl-235b-a22b-thinking

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

qwen3-vl-235b-a22b-thinking

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks