Model profile · Qwen

Qwen3.5 35B A3B

Open weightsbudget · registry tag 2026 open moe incremental

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 15.1%
Verified coverage: 15.1%
Spread: 67.8%
Last verified: Jun 20, 2026

55%bench fit

textcodedocumentvision6 aliases32 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

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

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

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

Chat / text29 benchmarks63%

Intelligence Index

AA · Chat / text · Combined

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

Rank #95 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 23
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

76.2% percentile inside its fair comparison set

23Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

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

Rank #179 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.7%
Percentile: 40.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

40.3% percentile inside its fair comparison set

15.7%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

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

Rank #241 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7.9%
Percentile: 19.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

19.5% percentile inside its fair comparison set

7.9%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #125 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.5%
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

60.6% percentile inside its fair comparison set

44.5%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

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

Rank #138 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.7 /1M tokens
Percentile: 50.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

50.4% percentile inside its fair comparison set

$0.7 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #115 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M input tokens
Percentile: 59.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

59.8% percentile inside its fair comparison set

$0.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #155 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M output tokens
Percentile: 45.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

45.3% percentile inside its fair comparison set

$2 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

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

Rank #46 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 161.6 tokens/s
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

78.6% percentile inside its fair comparison set

161.6 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #100 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.24s
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

52.9% percentile inside its fair comparison set

2.24sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

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

Rank #112 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14.62s
Percentile: 47.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

47.1% percentile inside its fair comparison set

14.62sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #114 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

54.8% percentile inside its fair comparison set

39Raw benchmark value

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 #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #124. Votes: 29248. Organization: alibaba. License: Apache 2.0.

68.9% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,400

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 #119 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,344
Percentile: 63.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: creative_writing. Source rank: #144. Votes: 4499. Organization: alibaba. License: Apache 2.0.

63.5% percentile inside its fair comparison set

1,344Raw benchmark valueCI 1,334 - 1,353

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 #100 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: english. Source rank: #121. Votes: 13761. Organization: alibaba. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,406 - 1,417

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 #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: exclude_ties. Source rank: #124. Votes: 21373. Organization: alibaba. License: Apache 2.0.

68.9% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,370 - 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 #109 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts. Source rank: #131. Votes: 18409. Organization: alibaba. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,408 - 1,419

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 #105 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 67.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts_english. Source rank: #128. Votes: 9004. Organization: alibaba. License: Apache 2.0.

67.9% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,417 - 1,430

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 #97 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: instruction_following. Source rank: #120. Votes: 9340. Organization: alibaba. License: Apache 2.0.

70.5% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,382 - 1,395

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 #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: longer_query. Source rank: #127. Votes: 11132. Organization: alibaba. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,396 - 1,409

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 #103 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 68.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: multi_turn. Source rank: #126. Votes: 5203. Organization: alibaba. License: Apache 2.0.

68.4% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,386 - 1,404

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 #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 70.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #118. Votes: 29248. Organization: alibaba. License: Apache 2.0.

70.2% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,400

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 #103 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,348
Percentile: 68.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: creative_writing. Source rank: #127. Votes: 4499. Organization: alibaba. License: Apache 2.0.

68.4% percentile inside its fair comparison set

1,348Raw benchmark valueCI 1,339 - 1,357

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 #97 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: english. Source rank: #116. Votes: 13761. Organization: alibaba. License: Apache 2.0.

70.5% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,402 - 1,414

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 #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 70.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: exclude_ties. Source rank: #118. Votes: 21373. Organization: alibaba. License: Apache 2.0.

70.2% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,369 - 1,380

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 #99 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 69.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts. Source rank: #120. Votes: 18409. Organization: alibaba. License: Apache 2.0.

69.8% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,395 - 1,406

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 #95 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 71%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts_english. Source rank: #115. Votes: 9004. Organization: alibaba. License: Apache 2.0.

71% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,402 - 1,416

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 #93 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 71.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: instruction_following. Source rank: #113. Votes: 9340. Organization: alibaba. License: Apache 2.0.

71.7% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,373 - 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 #95 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: longer_query. Source rank: #117. Votes: 11132. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,386 - 1,399

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 #100 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 69.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: multi_turn. Source rank: #121. Votes: 5203. Organization: alibaba. License: Apache 2.0.

69.3% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,382 - 1,399

Coding8 benchmarks39%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #144 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.6%
Percentile: 52.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

52.6% percentile inside its fair comparison set

10.6%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #180 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29.3%
Percentile: 51.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

51.4% percentile inside its fair comparison set

29.3%Raw benchmark value

Code Arena

AR · Coding · Human

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

Rank #61 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 17.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #76. Votes: 1814. Organization: alibaba. License: Apache 2.0.

17.8% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,234 - 1,265

WebDev Arena

AR · Coding · Human

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

Rank #61 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 17.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: webdev. Source rank: #76. Votes: 1814. Organization: alibaba. License: Apache 2.0.

17.8% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,234 - 1,265

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #54 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,316
Percentile: 27.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: webdev-html. Source rank: #67. Votes: 251. Organization: alibaba. License: Apache 2.0.

27.4% percentile inside its fair comparison set

1,316Raw benchmark valueCI 1,279 - 1,353

Code Arena · Webdev React

AR · Coding · Human

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

Rank #55 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 8.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: webdev-react. Source rank: #69. Votes: 1563. Organization: alibaba. License: Apache 2.0.

8.5% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,215 - 1,249

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 #108 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 66.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: coding. Source rank: #130. Votes: 8001. Organization: alibaba. License: Apache 2.0.

66.6% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,428 - 1,442

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 #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: coding. Source rank: #117. Votes: 8001. Organization: alibaba. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,402 - 1,417

Reasoning / math / science5 benchmarks77.7%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

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

Rank #69 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.8%
Percentile: 81.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

81.6% percentile inside its fair comparison set

12.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #55 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 81.9%
Percentile: 85.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

85.6% percentile inside its fair comparison set

81.9%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #66 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.6%
Percentile: 80.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

80.1% percentile inside its fair comparison set

0.6%Raw benchmark value

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 #96 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: math. Source rank: #119. Votes: 1764. Organization: alibaba. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,386 - 1,414

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 #91 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 71.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: math. Source rank: #109. Votes: 1764. Organization: alibaba. License: Apache 2.0.

71.3% percentile inside its fair comparison set

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

Professional reasoning18 benchmarks69.2%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #93 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: expert. Source rank: #113. Votes: 2531. Organization: alibaba. License: Apache 2.0.

66.5% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,408 - 1,432

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 #94 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 70.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_business_and_management_and_financial_operations. Source rank: #114. Votes: 5873. Organization: alibaba. License: Apache 2.0.

70.8% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,394 - 1,410

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 #116 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_entertainment_and_sports_and_media. Source rank: #142. Votes: 5700. Organization: alibaba. License: Apache 2.0.

64.4% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,338 - 1,354

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_legal_and_government. Source rank: #125. Votes: 2277. Organization: alibaba. License: Apache 2.0.

66.1% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,388 - 1,414

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 #99 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_life_and_physical_and_social_science. Source rank: #121. Votes: 4942. Organization: alibaba. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,424

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_mathematical. Source rank: #121. Votes: 1586. Organization: alibaba. License: Apache 2.0.

68.5% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,393 - 1,424

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #91 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_medicine_and_healthcare. Source rank: #111. Votes: 2168. Organization: alibaba. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,419 - 1,445

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 #101 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 69.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_software_and_it_services. Source rank: #121. Votes: 11524. Organization: alibaba. License: Apache 2.0.

69.2% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,425 - 1,437

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 #112 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_writing_and_literature_and_language. Source rank: #137. Votes: 6698. Organization: alibaba. License: Apache 2.0.

65.7% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,358 - 1,373

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #85 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: expert. Source rank: #103. Votes: 2531. Organization: alibaba. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,395 - 1,419

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 #89 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 72.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_business_and_management_and_financial_operations. Source rank: #107. Votes: 5873. Organization: alibaba. License: Apache 2.0.

72.3% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,386 - 1,402

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 #104 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,348
Percentile: 68.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_entertainment_and_sports_and_media. Source rank: #127. Votes: 5700. Organization: alibaba. License: Apache 2.0.

68.1% percentile inside its fair comparison set

1,348Raw benchmark valueCI 1,340 - 1,356

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 #96 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 68.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_legal_and_government. Source rank: #117. Votes: 2277. Organization: alibaba. License: Apache 2.0.

68.1% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,387 - 1,413

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 #96 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 70.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_life_and_physical_and_social_science. Source rank: #115. Votes: 4942. Organization: alibaba. License: Apache 2.0.

70.6% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,403 - 1,421

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #92 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_mathematical. Source rank: #110. Votes: 1586. Organization: alibaba. License: Apache 2.0.

70.5% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,392 - 1,422

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 #74 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 75.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_medicine_and_healthcare. Source rank: #87. Votes: 2168. Organization: alibaba. License: Apache 2.0.

75.3% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,414 - 1,441

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 #94 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_software_and_it_services. Source rank: #112. Votes: 11524. Organization: alibaba. License: Apache 2.0.

71.4% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,409 - 1,422

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 #101 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_writing_and_literature_and_language. Source rank: #124. Votes: 6698. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,358 - 1,374

Search / tool use1 benchmark82.8%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #55 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.3%
Percentile: 82.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

82.8% percentile inside its fair comparison set

86.3%Raw benchmark value

Long context1 benchmark78.1%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #70 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.3%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

78.1% percentile inside its fair comparison set

55.3%Raw benchmark value

Vision understanding1 benchmark74.1%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #37 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.2%
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

74.1% percentile inside its fair comparison set

69.2%Raw benchmark value

Multilingual14 benchmarks62.8%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #70 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 76.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: chinese. Source rank: #84. Votes: 1615. Organization: alibaba. License: Apache 2.0.

76.6% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,447 - 1,479

Text Arena · French

AR · Multilingual · Human

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

Rank #83 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: french. Source rank: #102. Votes: 835. Organization: alibaba. License: Apache 2.0.

62% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,402 - 1,447

Text Arena · German

AR · Multilingual · Human

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

Rank #118 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,348
Percentile: 50.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: german. Source rank: #143. Votes: 480. Organization: alibaba. License: Apache 2.0.

50.6% percentile inside its fair comparison set

1,348Raw benchmark valueCI 1,322 - 1,375

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #90 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 56.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: japanese. Source rank: #112. Votes: 223. Organization: alibaba. License: Apache 2.0.

56.2% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,282 - 1,365

Text Arena · Korean

AR · Multilingual · Human

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

Rank #86 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: korean. Source rank: #106. Votes: 469. Organization: alibaba. License: Apache 2.0.

59.1% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,318 - 1,374

Text Arena · Russian

AR · Multilingual · Human

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

Rank #107 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: russian. Source rank: #130. Votes: 3165. Organization: alibaba. License: Apache 2.0.

63.3% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,368 - 1,390

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #94 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 56.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: spanish. Source rank: #116. Votes: 895. Organization: alibaba. License: Apache 2.0.

56.5% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,365 - 1,407

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #51 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: chinese. Source rank: #61. Votes: 1615. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,452 - 1,483

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 63%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: french. Source rank: #97. Votes: 835. Organization: alibaba. License: Apache 2.0.

63% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,394 - 1,438

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #103 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: german. Source rank: #125. Votes: 480. Organization: alibaba. License: Apache 2.0.

57% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,332 - 1,384

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #77 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,332
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: japanese. Source rank: #96. Votes: 223. Organization: alibaba. License: Apache 2.0.

62.6% percentile inside its fair comparison set

1,332Raw benchmark valueCI 1,291 - 1,374

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: korean. Source rank: #96. Votes: 469. Organization: alibaba. License: Apache 2.0.

62.5% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,326 - 1,382

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 66.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: russian. Source rank: #120. Votes: 3165. Organization: alibaba. License: Apache 2.0.

66.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,368 - 1,390

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #87 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 59.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: spanish. Source rank: #105. Votes: 895. Organization: alibaba. License: Apache 2.0.

59.8% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,371 - 1,413

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

Model profile · Qwen

Qwen3.5 35B A3B

Open weightsbudget · registry tag 2026 open moe incremental

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 15.1%
Verified coverage: 15.1%
Spread: 67.8%
Last verified: Jun 20, 2026

55%bench fit

textcodedocumentvision6 aliases32 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

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

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

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

Chat / text29 benchmarks63%

Intelligence Index

AA · Chat / text · Combined

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

Rank #95 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 23
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

76.2% percentile inside its fair comparison set

23Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

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

Rank #179 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.7%
Percentile: 40.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

40.3% percentile inside its fair comparison set

15.7%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

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

Rank #241 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7.9%
Percentile: 19.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

19.5% percentile inside its fair comparison set

7.9%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #125 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.5%
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

60.6% percentile inside its fair comparison set

44.5%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

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

Rank #138 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.7 /1M tokens
Percentile: 50.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

50.4% percentile inside its fair comparison set

$0.7 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #115 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M input tokens
Percentile: 59.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

59.8% percentile inside its fair comparison set

$0.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #155 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M output tokens
Percentile: 45.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

45.3% percentile inside its fair comparison set

$2 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

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

Rank #46 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 161.6 tokens/s
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

78.6% percentile inside its fair comparison set

161.6 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #100 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.24s
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

52.9% percentile inside its fair comparison set

2.24sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

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

Rank #112 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14.62s
Percentile: 47.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

47.1% percentile inside its fair comparison set

14.62sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #114 · Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

54.8% percentile inside its fair comparison set

39Raw benchmark value

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 #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #124. Votes: 29248. Organization: alibaba. License: Apache 2.0.

68.9% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,400

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 #119 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,344
Percentile: 63.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: creative_writing. Source rank: #144. Votes: 4499. Organization: alibaba. License: Apache 2.0.

63.5% percentile inside its fair comparison set

1,344Raw benchmark valueCI 1,334 - 1,353

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 #100 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: english. Source rank: #121. Votes: 13761. Organization: alibaba. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,406 - 1,417

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 #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: exclude_ties. Source rank: #124. Votes: 21373. Organization: alibaba. License: Apache 2.0.

68.9% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,370 - 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 #109 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts. Source rank: #131. Votes: 18409. Organization: alibaba. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,408 - 1,419

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 #105 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 67.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts_english. Source rank: #128. Votes: 9004. Organization: alibaba. License: Apache 2.0.

67.9% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,417 - 1,430

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 #97 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: instruction_following. Source rank: #120. Votes: 9340. Organization: alibaba. License: Apache 2.0.

70.5% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,382 - 1,395

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 #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: longer_query. Source rank: #127. Votes: 11132. Organization: alibaba. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,396 - 1,409

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 #103 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 68.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: multi_turn. Source rank: #126. Votes: 5203. Organization: alibaba. License: Apache 2.0.

68.4% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,386 - 1,404

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 #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 70.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #118. Votes: 29248. Organization: alibaba. License: Apache 2.0.

70.2% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,400

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 #103 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,348
Percentile: 68.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: creative_writing. Source rank: #127. Votes: 4499. Organization: alibaba. License: Apache 2.0.

68.4% percentile inside its fair comparison set

1,348Raw benchmark valueCI 1,339 - 1,357

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 #97 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: english. Source rank: #116. Votes: 13761. Organization: alibaba. License: Apache 2.0.

70.5% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,402 - 1,414

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 #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 70.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: exclude_ties. Source rank: #118. Votes: 21373. Organization: alibaba. License: Apache 2.0.

70.2% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,369 - 1,380

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 #99 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 69.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts. Source rank: #120. Votes: 18409. Organization: alibaba. License: Apache 2.0.

69.8% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,395 - 1,406

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 #95 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 71%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts_english. Source rank: #115. Votes: 9004. Organization: alibaba. License: Apache 2.0.

71% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,402 - 1,416

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 #93 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 71.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: instruction_following. Source rank: #113. Votes: 9340. Organization: alibaba. License: Apache 2.0.

71.7% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,373 - 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 #95 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: longer_query. Source rank: #117. Votes: 11132. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,386 - 1,399

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 #100 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 69.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: multi_turn. Source rank: #121. Votes: 5203. Organization: alibaba. License: Apache 2.0.

69.3% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,382 - 1,399

Coding8 benchmarks39%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #144 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.6%
Percentile: 52.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

52.6% percentile inside its fair comparison set

10.6%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #180 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29.3%
Percentile: 51.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

51.4% percentile inside its fair comparison set

29.3%Raw benchmark value

Code Arena

AR · Coding · Human

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

Rank #61 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 17.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #76. Votes: 1814. Organization: alibaba. License: Apache 2.0.

17.8% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,234 - 1,265

WebDev Arena

AR · Coding · Human

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

Rank #61 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 17.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: webdev. Source rank: #76. Votes: 1814. Organization: alibaba. License: Apache 2.0.

17.8% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,234 - 1,265

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #54 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,316
Percentile: 27.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: webdev-html. Source rank: #67. Votes: 251. Organization: alibaba. License: Apache 2.0.

27.4% percentile inside its fair comparison set

1,316Raw benchmark valueCI 1,279 - 1,353

Code Arena · Webdev React

AR · Coding · Human

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

Rank #55 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 8.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: webdev-react. Source rank: #69. Votes: 1563. Organization: alibaba. License: Apache 2.0.

8.5% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,215 - 1,249

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 #108 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 66.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: coding. Source rank: #130. Votes: 8001. Organization: alibaba. License: Apache 2.0.

66.6% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,428 - 1,442

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 #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: coding. Source rank: #117. Votes: 8001. Organization: alibaba. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,402 - 1,417

Reasoning / math / science5 benchmarks77.7%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

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

Rank #69 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.8%
Percentile: 81.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

81.6% percentile inside its fair comparison set

12.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #55 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 81.9%
Percentile: 85.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

85.6% percentile inside its fair comparison set

81.9%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #66 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.6%
Percentile: 80.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

80.1% percentile inside its fair comparison set

0.6%Raw benchmark value

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 #96 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: math. Source rank: #119. Votes: 1764. Organization: alibaba. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,386 - 1,414

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 #91 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 71.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: math. Source rank: #109. Votes: 1764. Organization: alibaba. License: Apache 2.0.

71.3% percentile inside its fair comparison set

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

Professional reasoning18 benchmarks69.2%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #93 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: expert. Source rank: #113. Votes: 2531. Organization: alibaba. License: Apache 2.0.

66.5% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,408 - 1,432

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 #94 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 70.8%
Last updated: recent
Eligibility: headline eligible

70.8% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,394 - 1,410

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 #116 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_entertainment_and_sports_and_media. Source rank: #142. Votes: 5700. Organization: alibaba. License: Apache 2.0.

64.4% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,338 - 1,354

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #102 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_legal_and_government. Source rank: #125. Votes: 2277. Organization: alibaba. License: Apache 2.0.

66.1% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,388 - 1,414

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 #99 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_life_and_physical_and_social_science. Source rank: #121. Votes: 4942. Organization: alibaba. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,424

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_mathematical. Source rank: #121. Votes: 1586. Organization: alibaba. License: Apache 2.0.

68.5% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,393 - 1,424

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #91 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_medicine_and_healthcare. Source rank: #111. Votes: 2168. Organization: alibaba. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,419 - 1,445

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 #101 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 69.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_software_and_it_services. Source rank: #121. Votes: 11524. Organization: alibaba. License: Apache 2.0.

69.2% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,425 - 1,437

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 #112 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_writing_and_literature_and_language. Source rank: #137. Votes: 6698. Organization: alibaba. License: Apache 2.0.

65.7% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,358 - 1,373

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #85 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: expert. Source rank: #103. Votes: 2531. Organization: alibaba. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,395 - 1,419

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 #89 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 72.3%
Last updated: recent
Eligibility: headline eligible

72.3% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,386 - 1,402

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 #104 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,348
Percentile: 68.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_entertainment_and_sports_and_media. Source rank: #127. Votes: 5700. Organization: alibaba. License: Apache 2.0.

68.1% percentile inside its fair comparison set

1,348Raw benchmark valueCI 1,340 - 1,356

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 #96 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 68.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_legal_and_government. Source rank: #117. Votes: 2277. Organization: alibaba. License: Apache 2.0.

68.1% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,387 - 1,413

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 #96 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 70.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_life_and_physical_and_social_science. Source rank: #115. Votes: 4942. Organization: alibaba. License: Apache 2.0.

70.6% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,403 - 1,421

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #92 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_mathematical. Source rank: #110. Votes: 1586. Organization: alibaba. License: Apache 2.0.

70.5% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,392 - 1,422

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 #74 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 75.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_medicine_and_healthcare. Source rank: #87. Votes: 2168. Organization: alibaba. License: Apache 2.0.

75.3% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,414 - 1,441

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 #94 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_software_and_it_services. Source rank: #112. Votes: 11524. Organization: alibaba. License: Apache 2.0.

71.4% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,409 - 1,422

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 #101 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: industry_writing_and_literature_and_language. Source rank: #124. Votes: 6698. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,358 - 1,374

Search / tool use1 benchmark82.8%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #55 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.3%
Percentile: 82.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

82.8% percentile inside its fair comparison set

86.3%Raw benchmark value

Long context1 benchmark78.1%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #70 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.3%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

78.1% percentile inside its fair comparison set

55.3%Raw benchmark value

Vision understanding1 benchmark74.1%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #37 · Source label: Qwen3.5 35B A3B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.2%
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

74.1% percentile inside its fair comparison set

69.2%Raw benchmark value

Multilingual14 benchmarks62.8%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #70 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 76.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: chinese. Source rank: #84. Votes: 1615. Organization: alibaba. License: Apache 2.0.

76.6% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,447 - 1,479

Text Arena · French

AR · Multilingual · Human

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

Rank #83 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: french. Source rank: #102. Votes: 835. Organization: alibaba. License: Apache 2.0.

62% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,402 - 1,447

Text Arena · German

AR · Multilingual · Human

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

Rank #118 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,348
Percentile: 50.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: german. Source rank: #143. Votes: 480. Organization: alibaba. License: Apache 2.0.

50.6% percentile inside its fair comparison set

1,348Raw benchmark valueCI 1,322 - 1,375

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #90 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 56.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: japanese. Source rank: #112. Votes: 223. Organization: alibaba. License: Apache 2.0.

56.2% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,282 - 1,365

Text Arena · Korean

AR · Multilingual · Human

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

Rank #86 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: korean. Source rank: #106. Votes: 469. Organization: alibaba. License: Apache 2.0.

59.1% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,318 - 1,374

Text Arena · Russian

AR · Multilingual · Human

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

Rank #107 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: russian. Source rank: #130. Votes: 3165. Organization: alibaba. License: Apache 2.0.

63.3% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,368 - 1,390

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #94 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 56.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: spanish. Source rank: #116. Votes: 895. Organization: alibaba. License: Apache 2.0.

56.5% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,365 - 1,407

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #51 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: chinese. Source rank: #61. Votes: 1615. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,452 - 1,483

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 63%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: french. Source rank: #97. Votes: 835. Organization: alibaba. License: Apache 2.0.

63% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,394 - 1,438

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #103 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: german. Source rank: #125. Votes: 480. Organization: alibaba. License: Apache 2.0.

57% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,332 - 1,384

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #77 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,332
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: japanese. Source rank: #96. Votes: 223. Organization: alibaba. License: Apache 2.0.

62.6% percentile inside its fair comparison set

1,332Raw benchmark valueCI 1,291 - 1,374

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: korean. Source rank: #96. Votes: 469. Organization: alibaba. License: Apache 2.0.

62.5% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,326 - 1,382

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #98 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 66.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: russian. Source rank: #120. Votes: 3165. Organization: alibaba. License: Apache 2.0.

66.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,368 - 1,390

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #87 · Source label: qwen3.5-35b-a3b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 59.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: spanish. Source rank: #105. Votes: 895. Organization: alibaba. License: Apache 2.0.

59.8% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,371 - 1,413