Model profile · Qwen

Qwen3.5 397B A17B

Open weightsfrontier · registry tag 2026 hosted flagship

Thin verified coverage

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

Visible coverage: 14.4%
Verified coverage: 14.4%
Spread: n/a
Last verified: Oct 3, 2026

textcodevisiondocument6 aliases43 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text27 benchmarksn/a

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 #179 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18
Percentile: 67.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

67.9% percentile inside its fair comparison set

18Raw 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 #168 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.5%
Percentile: 63.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

63.1% percentile inside its fair comparison set

24.5%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 #317 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.1%
Percentile: 30.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

30.2% percentile inside its fair comparison set

11.1%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 #101 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.6%
Percentile: 71.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

71.3% percentile inside its fair comparison set

51.6%Raw 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 #194 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.6 /1M input tokens
Percentile: 45.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

45.8% percentile inside its fair comparison set

$0.6 /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 #214 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.6 /1M output tokens
Percentile: 39.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

39.8% percentile inside its fair comparison set

$3.6 /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 #133 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 84.4 tokens/s
Percentile: 49.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

49.6% percentile inside its fair comparison set

84.4 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 #102 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.22s
Percentile: 61.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

61.7% percentile inside its fair comparison set

2.22sRaw 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 #196 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.63s
Percentile: 25.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

25.6% percentile inside its fair comparison set

38.63sRaw 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 #84 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #92. Votes: 88660. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,439 - 1,445

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 #91 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 75.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing. Source rank: #101. Votes: 15506. Organization: alibaba. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,400 - 1,411

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 #87 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 77.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #95. Votes: 39280. Organization: alibaba. License: Apache 2.0.

77.1% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,446 - 1,454

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 #85 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 77.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: exclude_ties. Source rank: #93. Votes: 64953. Organization: alibaba. License: Apache 2.0.

77.7% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,436 - 1,445

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 #80 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 79%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts. Source rank: #88. Votes: 58533. Organization: alibaba. License: Apache 2.0.

79% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,460 - 1,467

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 #82 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 78.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts_english. Source rank: #90. Votes: 26470. Organization: alibaba. License: Apache 2.0.

78.3% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,463 - 1,473

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 #83 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: instruction_following. Source rank: #90. Votes: 30250. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,429 - 1,438

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 #76 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 78.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: longer_query. Source rank: #83. Votes: 39082. Organization: alibaba. License: Apache 2.0.

78.9% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,449 - 1,458

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 #75 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 80.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: multi_turn. Source rank: #83. Votes: 14488. Organization: alibaba. License: Apache 2.0.

80.2% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,448 - 1,459

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 #74 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #80. Votes: 88660. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,435 - 1,441

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 #86 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 77.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing. Source rank: #95. Votes: 15506. Organization: alibaba. License: Apache 2.0.

77.3% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,396 - 1,407

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 #80 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 79%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #85. Votes: 39280. Organization: alibaba. License: Apache 2.0.

79% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,439 - 1,448

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 #73 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: exclude_ties. Source rank: #79. Votes: 64953. Organization: alibaba. License: Apache 2.0.

80.9% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,429 - 1,438

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 #74 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 80.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts. Source rank: #78. Votes: 58533. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,444 - 1,452

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 #78 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts_english. Source rank: #81. Votes: 26470. Organization: alibaba. License: Apache 2.0.

79.4% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,446 - 1,456

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 #76 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 80.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: instruction_following. Source rank: #80. Votes: 30250. Organization: alibaba. License: Apache 2.0.

80.1% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,419 - 1,428

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 #69 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 80.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: longer_query. Source rank: #73. Votes: 39082. Organization: alibaba. License: Apache 2.0.

80.8% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,438 - 1,446

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 #66 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 82.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: multi_turn. Source rank: #72. Votes: 14488. Organization: alibaba. License: Apache 2.0.

82.6% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,441 - 1,453

Coding7 benchmarksn/a

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 #39 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35.6%
Percentile: 88.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

88.9% percentile inside its fair comparison set

35.6%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 #115 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.8%
Percentile: 42.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

42.4% percentile inside its fair comparison set

44.8%Raw benchmark value

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 #83 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: coding. Source rank: #90. Votes: 25317. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,486 - 1,496

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 #73 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 80.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: coding. Source rank: #77. Votes: 25317. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,459 - 1,469

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 #83 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 35.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #86. Votes: 21280. Organization: alibaba. License: Apache 2.0.

35.4% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,394 - 1,405

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 #80 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 36.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: webdev-html. Source rank: #85. Votes: 2607. Organization: alibaba. License: Apache 2.0.

36.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,397 - 1,421

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 #79 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 31%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: webdev-react. Source rank: #84. Votes: 16871. Organization: alibaba. License: Apache 2.0.

31% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,381 - 1,393

Reasoning / math / science5 benchmarksn/a

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 #149 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 19.8%
Percentile: 72%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

72% percentile inside its fair comparison set

19.8%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 #76 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.1%
Percentile: 84.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

84.8% percentile inside its fair comparison set

86.1%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 #161 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.9%
Percentile: 65.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.4% percentile inside its fair comparison set

0.9%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 #66 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: math. Source rank: #72. Votes: 4839. Organization: alibaba. License: Apache 2.0.

81.9% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,443 - 1,461

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 #60 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 83.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: math. Source rank: #63. Votes: 4839. Organization: alibaba. License: Apache 2.0.

83.6% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,446 - 1,464

Professional reasoning19 benchmarksn/a

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #22 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.3%
Percentile: 34.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

34.4% percentile inside its fair comparison set

15.3%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #72 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 78.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: expert. Source rank: #76. Votes: 9511. Organization: alibaba. License: Apache 2.0.

78.3% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,470 - 1,484

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 #77 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_business_and_management_and_financial_operations. Source rank: #85. Votes: 17752. Organization: alibaba. License: Apache 2.0.

79.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,441 - 1,451

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 #96 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 74.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_entertainment_and_sports_and_media. Source rank: #105. Votes: 19935. Organization: alibaba. License: Apache 2.0.

74.6% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,397 - 1,407

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #90 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 74.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_legal_and_government. Source rank: #102. Votes: 6790. Organization: alibaba. License: Apache 2.0.

74.5% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,438 - 1,453

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 #78 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_life_and_physical_and_social_science. Source rank: #85. Votes: 14475. Organization: alibaba. License: Apache 2.0.

79.4% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,459 - 1,470

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #69 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_mathematical. Source rank: #75. Votes: 5165. Organization: alibaba. License: Apache 2.0.

80.9% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,446 - 1,463

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #74 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 78.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_medicine_and_healthcare. Source rank: #81. Votes: 6635. Organization: alibaba. License: Apache 2.0.

78.9% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,459 - 1,475

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 #84 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_software_and_it_services. Source rank: #92. Votes: 35632. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,477 - 1,485

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 #84 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_writing_and_literature_and_language. Source rank: #93. Votes: 21785. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,416 - 1,426

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #63 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 81%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: expert. Source rank: #66. Votes: 9511. Organization: alibaba. License: Apache 2.0.

81% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,455 - 1,469

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 #61 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 83.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_business_and_management_and_financial_operations. Source rank: #64. Votes: 17752. Organization: alibaba. License: Apache 2.0.

83.7% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,429 - 1,440

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 #92 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 75.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_entertainment_and_sports_and_media. Source rank: #99. Votes: 19935. Organization: alibaba. License: Apache 2.0.

75.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,393 - 1,403

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 #77 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_legal_and_government. Source rank: #82. Votes: 6790. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,433 - 1,449

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 #64 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 83.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_life_and_physical_and_social_science. Source rank: #67. Votes: 14475. Organization: alibaba. License: Apache 2.0.

83.2% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,451 - 1,462

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #65 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_mathematical. Source rank: #68. Votes: 5165. Organization: alibaba. License: Apache 2.0.

82% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,445 - 1,462

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 #58 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 83.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_medicine_and_healthcare. Source rank: #59. Votes: 6635. Organization: alibaba. License: Apache 2.0.

83.5% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,448 - 1,464

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 #68 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_software_and_it_services. Source rank: #71. Votes: 35632. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,459 - 1,467

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 #75 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 80.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_writing_and_literature_and_language. Source rank: #82. Votes: 21785. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,410 - 1,420

Search / tool use1 benchmarkn/a

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 #72 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 83.9%
Percentile: 79.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

79.1% percentile inside its fair comparison set

83.9%Raw benchmark value

Long context1 benchmarkn/a

Long Context Reasoning

AA · Long context · Objective

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

Rank #174 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.3%
Percentile: 62%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

62% percentile inside its fair comparison set

64.3%Raw benchmark value

Vision understanding19 benchmarksn/a

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 #166 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 52.7%
Percentile: 20.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

20.7% percentile inside its fair comparison set

52.7%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #49 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,247
Percentile: 65.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #54. Votes: 31441. Organization: alibaba. License: Apache 2.0.

65.5% percentile inside its fair comparison set

1,247Raw benchmark valueCI 1,242 - 1,252

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #22 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,178
Percentile: 32.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: captioning. Source rank: #22. Votes: 77. Organization: alibaba. License: Apache 2.0.

32.3% percentile inside its fair comparison set

1,178Raw benchmark valueCI 1,120 - 1,235

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #40 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,246
Percentile: 52.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing_vision. Source rank: #45. Votes: 2200. Organization: alibaba. License: Apache 2.0.

52.4% percentile inside its fair comparison set

1,246Raw benchmark valueCI 1,233 - 1,259

Vision Arena · Diagram

AR · Vision understanding · Human

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

Rank #45 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,274
Percentile: 55.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: diagram. Source rank: #50. Votes: 8276. Organization: alibaba. License: Apache 2.0.

55.6% percentile inside its fair comparison set

1,274Raw benchmark valueCI 1,267 - 1,282

Vision Arena · English

AR · Vision understanding · Human

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

Rank #46 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,251
Percentile: 67.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #50. Votes: 12215. Organization: alibaba. License: Apache 2.0.

67.4% percentile inside its fair comparison set

1,251Raw benchmark valueCI 1,243 - 1,258

Vision Arena · Entity Recognition

AR · Vision understanding · Human

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

Rank #23 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,213
Percentile: 45%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: entity_recognition. Source rank: #26. Votes: 218. Organization: alibaba. License: Apache 2.0.

45% percentile inside its fair comparison set

1,213Raw benchmark valueCI 1,175 - 1,251

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #42 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 57.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: homework. Source rank: #46. Votes: 3833. Organization: alibaba. License: Apache 2.0.

57.3% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,277 - 1,297

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #37 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,241
Percentile: 50.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: humor. Source rank: #42. Votes: 1178. Organization: alibaba. License: Apache 2.0.

50.7% percentile inside its fair comparison set

1,241Raw benchmark valueCI 1,224 - 1,259

Vision Arena · Ocr

AR · Vision understanding · Human

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

Rank #49 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,261
Percentile: 52%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: ocr. Source rank: #53. Votes: 21841. Organization: alibaba. License: Apache 2.0.

52% percentile inside its fair comparison set

1,261Raw benchmark valueCI 1,256 - 1,267

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #44 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,264
Percentile: 69.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #48. Votes: 31441. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,264Raw benchmark valueCI 1,258 - 1,269

Vision Arena · Captioning · No Style Control

AR · Vision understanding · Human

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

Rank #14 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 58.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: captioning. Source rank: #15. Votes: 77. Organization: alibaba. License: Apache 2.0.

58.1% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,174 - 1,289

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #34 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 59.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing_vision. Source rank: #39. Votes: 2200. Organization: alibaba. License: Apache 2.0.

59.8% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,249 - 1,276

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

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

Rank #44 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 56.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: diagram. Source rank: #47. Votes: 8276. Organization: alibaba. License: Apache 2.0.

56.6% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,271 - 1,286

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #42 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,269
Percentile: 70.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #45. Votes: 12215. Organization: alibaba. License: Apache 2.0.

70.3% percentile inside its fair comparison set

1,269Raw benchmark valueCI 1,262 - 1,277

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

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

Rank #12 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,267
Percentile: 72.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: entity_recognition. Source rank: #13. Votes: 218. Organization: alibaba. License: Apache 2.0.

72.5% percentile inside its fair comparison set

1,267Raw benchmark valueCI 1,230 - 1,304

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 61.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: homework. Source rank: #42. Votes: 3833. Organization: alibaba. License: Apache 2.0.

61.5% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,282 - 1,302

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #35 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 53.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: humor. Source rank: #40. Votes: 1178. Organization: alibaba. License: Apache 2.0.

53.4% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,244 - 1,279

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #44 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 57%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: ocr. Source rank: #48. Votes: 21841. Organization: alibaba. License: Apache 2.0.

57% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,266 - 1,277

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #58 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 83.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #61. Votes: 6096. Organization: alibaba. License: Apache 2.0.

83.8% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,490 - 1,506

Text Arena · French

AR · Multilingual · Human

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

Rank #67 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 74.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: french. Source rank: #75. Votes: 2840. Organization: alibaba. License: Apache 2.0.

74.3% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,456 - 1,482

Text Arena · German

AR · Multilingual · Human

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

Rank #66 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 76.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: german. Source rank: #75. Votes: 1364. Organization: alibaba. License: Apache 2.0.

76.1% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,429 - 1,463

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #50 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 79.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: japanese. Source rank: #56. Votes: 1032. Organization: alibaba. License: Apache 2.0.

79.8% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,409 - 1,449

Text Arena · Korean

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 67.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: korean. Source rank: #93. Votes: 1478. Organization: alibaba. License: Apache 2.0.

67.2% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,366 - 1,400

Text Arena · Non English

AR · Multilingual · Human

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

Rank #82 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 78.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: non_english. Source rank: #90. Votes: 49373. Organization: alibaba. License: Apache 2.0.

78.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,435

Text Arena · Polish

AR · Multilingual · Human

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

Rank #57 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 71.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: polish. Source rank: #68. Votes: 1583. Organization: alibaba. License: Apache 2.0.

71.9% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,434 - 1,464

Text Arena · Russian

AR · Multilingual · Human

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

Rank #87 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 74.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: russian. Source rank: #97. Votes: 10116. Organization: alibaba. License: Apache 2.0.

74.8% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,428 - 1,441

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #73 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 72.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: spanish. Source rank: #81. Votes: 2727. Organization: alibaba. License: Apache 2.0.

72.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,428 - 1,453

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #49 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 86.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #52. Votes: 6096. Organization: alibaba. License: Apache 2.0.

86.4% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,492 - 1,508

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #47 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 82.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: french. Source rank: #51. Votes: 2840. Organization: alibaba. License: Apache 2.0.

82.1% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,449 - 1,475

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #48 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 82.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: german. Source rank: #52. Votes: 1364. Organization: alibaba. License: Apache 2.0.

82.7% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,431 - 1,465

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #36 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 85.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: japanese. Source rank: #39. Votes: 1032. Organization: alibaba. License: Apache 2.0.

85.6% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,407 - 1,447

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 68%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: korean. Source rank: #88. Votes: 1478. Organization: alibaba. License: Apache 2.0.

68% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,365 - 1,399

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: non_english. Source rank: #74. Votes: 49373. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,426 - 1,434

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #40 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 80.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: polish. Source rank: #44. Votes: 1583. Organization: alibaba. License: Apache 2.0.

80.4% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,437 - 1,467

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #78 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: russian. Source rank: #84. Votes: 10116. Organization: alibaba. License: Apache 2.0.

77.4% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,422 - 1,435

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #69 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 73.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: spanish. Source rank: #74. Votes: 2727. Organization: alibaba. License: Apache 2.0.

73.7% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,430 - 1,455

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #42 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 60.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #46. Votes: 1985. Organization: alibaba. License: Apache 2.0.

60.6% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,276 - 1,308

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #36 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 66.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #40. Votes: 1985. Organization: alibaba. License: Apache 2.0.

66.3% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,299 - 1,330

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

Model profile · Qwen

Qwen3.5 397B A17B

Open weightsfrontier · registry tag 2026 hosted flagship

Thin verified coverage

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

Visible coverage: 14.4%
Verified coverage: 14.4%
Spread: n/a
Last verified: Oct 3, 2026

textcodevisiondocument6 aliases43 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

Chat / text27 benchmarksn/a

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 #179 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18
Percentile: 67.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

67.9% percentile inside its fair comparison set

18Raw 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 #168 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.5%
Percentile: 63.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

63.1% percentile inside its fair comparison set

24.5%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 #317 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.1%
Percentile: 30.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

30.2% percentile inside its fair comparison set

11.1%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 #101 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.6%
Percentile: 71.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

71.3% percentile inside its fair comparison set

51.6%Raw 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 #194 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.6 /1M input tokens
Percentile: 45.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

45.8% percentile inside its fair comparison set

$0.6 /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 #214 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.6 /1M output tokens
Percentile: 39.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

39.8% percentile inside its fair comparison set

$3.6 /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 #133 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 84.4 tokens/s
Percentile: 49.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

49.6% percentile inside its fair comparison set

84.4 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 #102 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.22s
Percentile: 61.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

61.7% percentile inside its fair comparison set

2.22sRaw 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 #196 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.63s
Percentile: 25.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

25.6% percentile inside its fair comparison set

38.63sRaw 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 #84 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #92. Votes: 88660. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,439 - 1,445

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 #91 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 75.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing. Source rank: #101. Votes: 15506. Organization: alibaba. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,400 - 1,411

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 #87 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 77.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #95. Votes: 39280. Organization: alibaba. License: Apache 2.0.

77.1% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,446 - 1,454

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 #85 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 77.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: exclude_ties. Source rank: #93. Votes: 64953. Organization: alibaba. License: Apache 2.0.

77.7% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,436 - 1,445

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 #80 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 79%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts. Source rank: #88. Votes: 58533. Organization: alibaba. License: Apache 2.0.

79% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,460 - 1,467

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 #82 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 78.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts_english. Source rank: #90. Votes: 26470. Organization: alibaba. License: Apache 2.0.

78.3% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,463 - 1,473

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 #83 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: instruction_following. Source rank: #90. Votes: 30250. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,429 - 1,438

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 #76 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 78.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: longer_query. Source rank: #83. Votes: 39082. Organization: alibaba. License: Apache 2.0.

78.9% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,449 - 1,458

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 #75 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 80.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: multi_turn. Source rank: #83. Votes: 14488. Organization: alibaba. License: Apache 2.0.

80.2% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,448 - 1,459

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 #74 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #80. Votes: 88660. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,435 - 1,441

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 #86 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 77.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing. Source rank: #95. Votes: 15506. Organization: alibaba. License: Apache 2.0.

77.3% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,396 - 1,407

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 #80 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 79%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #85. Votes: 39280. Organization: alibaba. License: Apache 2.0.

79% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,439 - 1,448

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 #73 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: exclude_ties. Source rank: #79. Votes: 64953. Organization: alibaba. License: Apache 2.0.

80.9% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,429 - 1,438

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 #74 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 80.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts. Source rank: #78. Votes: 58533. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,444 - 1,452

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 #78 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: hard_prompts_english. Source rank: #81. Votes: 26470. Organization: alibaba. License: Apache 2.0.

79.4% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,446 - 1,456

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 #76 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 80.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: instruction_following. Source rank: #80. Votes: 30250. Organization: alibaba. License: Apache 2.0.

80.1% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,419 - 1,428

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 #69 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 80.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: longer_query. Source rank: #73. Votes: 39082. Organization: alibaba. License: Apache 2.0.

80.8% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,438 - 1,446

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 #66 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 82.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: multi_turn. Source rank: #72. Votes: 14488. Organization: alibaba. License: Apache 2.0.

82.6% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,441 - 1,453

Coding7 benchmarksn/a

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 #39 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35.6%
Percentile: 88.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

88.9% percentile inside its fair comparison set

35.6%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 #115 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.8%
Percentile: 42.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

42.4% percentile inside its fair comparison set

44.8%Raw benchmark value

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 #83 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: coding. Source rank: #90. Votes: 25317. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,486 - 1,496

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 #73 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 80.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: coding. Source rank: #77. Votes: 25317. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,459 - 1,469

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 #83 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 35.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #86. Votes: 21280. Organization: alibaba. License: Apache 2.0.

35.4% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,394 - 1,405

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 #80 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 36.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: webdev-html. Source rank: #85. Votes: 2607. Organization: alibaba. License: Apache 2.0.

36.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,397 - 1,421

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 #79 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 31%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: webdev-react. Source rank: #84. Votes: 16871. Organization: alibaba. License: Apache 2.0.

31% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,381 - 1,393

Reasoning / math / science5 benchmarksn/a

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 #149 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 19.8%
Percentile: 72%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

72% percentile inside its fair comparison set

19.8%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 #76 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.1%
Percentile: 84.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

84.8% percentile inside its fair comparison set

86.1%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 #161 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.9%
Percentile: 65.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.4% percentile inside its fair comparison set

0.9%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 #66 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: math. Source rank: #72. Votes: 4839. Organization: alibaba. License: Apache 2.0.

81.9% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,443 - 1,461

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 #60 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 83.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: math. Source rank: #63. Votes: 4839. Organization: alibaba. License: Apache 2.0.

83.6% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,446 - 1,464

Professional reasoning19 benchmarksn/a

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #22 · Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.3%
Percentile: 34.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

34.4% percentile inside its fair comparison set

15.3%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #72 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 78.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: expert. Source rank: #76. Votes: 9511. Organization: alibaba. License: Apache 2.0.

78.3% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,470 - 1,484

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 #77 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

79.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,441 - 1,451

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 #96 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 74.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_entertainment_and_sports_and_media. Source rank: #105. Votes: 19935. Organization: alibaba. License: Apache 2.0.

74.6% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,397 - 1,407

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #90 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 74.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_legal_and_government. Source rank: #102. Votes: 6790. Organization: alibaba. License: Apache 2.0.

74.5% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,438 - 1,453

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 #78 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_life_and_physical_and_social_science. Source rank: #85. Votes: 14475. Organization: alibaba. License: Apache 2.0.

79.4% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,459 - 1,470

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #69 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_mathematical. Source rank: #75. Votes: 5165. Organization: alibaba. License: Apache 2.0.

80.9% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,446 - 1,463

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #74 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 78.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_medicine_and_healthcare. Source rank: #81. Votes: 6635. Organization: alibaba. License: Apache 2.0.

78.9% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,459 - 1,475

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 #84 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_software_and_it_services. Source rank: #92. Votes: 35632. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,477 - 1,485

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 #84 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_writing_and_literature_and_language. Source rank: #93. Votes: 21785. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,416 - 1,426

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #63 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 81%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: expert. Source rank: #66. Votes: 9511. Organization: alibaba. License: Apache 2.0.

81% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,455 - 1,469

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 #61 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 83.7%
Last updated: recent
Eligibility: preview_model

83.7% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,429 - 1,440

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 #92 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 75.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_entertainment_and_sports_and_media. Source rank: #99. Votes: 19935. Organization: alibaba. License: Apache 2.0.

75.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,393 - 1,403

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 #77 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_legal_and_government. Source rank: #82. Votes: 6790. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,433 - 1,449

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 #64 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 83.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_life_and_physical_and_social_science. Source rank: #67. Votes: 14475. Organization: alibaba. License: Apache 2.0.

83.2% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,451 - 1,462

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #65 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_mathematical. Source rank: #68. Votes: 5165. Organization: alibaba. License: Apache 2.0.

82% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,445 - 1,462

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 #58 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 83.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_medicine_and_healthcare. Source rank: #59. Votes: 6635. Organization: alibaba. License: Apache 2.0.

83.5% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,448 - 1,464

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 #68 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_software_and_it_services. Source rank: #71. Votes: 35632. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,459 - 1,467

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 #75 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 80.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: industry_writing_and_literature_and_language. Source rank: #82. Votes: 21785. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,410 - 1,420

Search / tool use1 benchmarkn/a

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 #72 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 83.9%
Percentile: 79.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

79.1% percentile inside its fair comparison set

83.9%Raw benchmark value

Long context1 benchmarkn/a

Long Context Reasoning

AA · Long context · Objective

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

Rank #174 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.3%
Percentile: 62%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

62% percentile inside its fair comparison set

64.3%Raw benchmark value

Vision understanding19 benchmarksn/a

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 #166 · Source label: Qwen3.5 397B A17B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 52.7%
Percentile: 20.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

20.7% percentile inside its fair comparison set

52.7%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #49 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,247
Percentile: 65.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #54. Votes: 31441. Organization: alibaba. License: Apache 2.0.

65.5% percentile inside its fair comparison set

1,247Raw benchmark valueCI 1,242 - 1,252

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #22 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,178
Percentile: 32.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: captioning. Source rank: #22. Votes: 77. Organization: alibaba. License: Apache 2.0.

32.3% percentile inside its fair comparison set

1,178Raw benchmark valueCI 1,120 - 1,235

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #40 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,246
Percentile: 52.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing_vision. Source rank: #45. Votes: 2200. Organization: alibaba. License: Apache 2.0.

52.4% percentile inside its fair comparison set

1,246Raw benchmark valueCI 1,233 - 1,259

Vision Arena · Diagram

AR · Vision understanding · Human

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

Rank #45 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,274
Percentile: 55.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: diagram. Source rank: #50. Votes: 8276. Organization: alibaba. License: Apache 2.0.

55.6% percentile inside its fair comparison set

1,274Raw benchmark valueCI 1,267 - 1,282

Vision Arena · English

AR · Vision understanding · Human

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

Rank #46 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,251
Percentile: 67.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #50. Votes: 12215. Organization: alibaba. License: Apache 2.0.

67.4% percentile inside its fair comparison set

1,251Raw benchmark valueCI 1,243 - 1,258

Vision Arena · Entity Recognition

AR · Vision understanding · Human

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

Rank #23 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,213
Percentile: 45%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: entity_recognition. Source rank: #26. Votes: 218. Organization: alibaba. License: Apache 2.0.

45% percentile inside its fair comparison set

1,213Raw benchmark valueCI 1,175 - 1,251

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #42 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 57.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: homework. Source rank: #46. Votes: 3833. Organization: alibaba. License: Apache 2.0.

57.3% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,277 - 1,297

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #37 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,241
Percentile: 50.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: humor. Source rank: #42. Votes: 1178. Organization: alibaba. License: Apache 2.0.

50.7% percentile inside its fair comparison set

1,241Raw benchmark valueCI 1,224 - 1,259

Vision Arena · Ocr

AR · Vision understanding · Human

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

Rank #49 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,261
Percentile: 52%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: ocr. Source rank: #53. Votes: 21841. Organization: alibaba. License: Apache 2.0.

52% percentile inside its fair comparison set

1,261Raw benchmark valueCI 1,256 - 1,267

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #44 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,264
Percentile: 69.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: overall. Source rank: #48. Votes: 31441. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,264Raw benchmark valueCI 1,258 - 1,269

Vision Arena · Captioning · No Style Control

AR · Vision understanding · Human

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

Rank #14 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 58.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: captioning. Source rank: #15. Votes: 77. Organization: alibaba. License: Apache 2.0.

58.1% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,174 - 1,289

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #34 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 59.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: creative_writing_vision. Source rank: #39. Votes: 2200. Organization: alibaba. License: Apache 2.0.

59.8% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,249 - 1,276

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

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

Rank #44 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 56.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: diagram. Source rank: #47. Votes: 8276. Organization: alibaba. License: Apache 2.0.

56.6% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,271 - 1,286

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #42 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,269
Percentile: 70.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: english. Source rank: #45. Votes: 12215. Organization: alibaba. License: Apache 2.0.

70.3% percentile inside its fair comparison set

1,269Raw benchmark valueCI 1,262 - 1,277

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

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

Rank #12 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,267
Percentile: 72.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: entity_recognition. Source rank: #13. Votes: 218. Organization: alibaba. License: Apache 2.0.

72.5% percentile inside its fair comparison set

1,267Raw benchmark valueCI 1,230 - 1,304

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 61.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: homework. Source rank: #42. Votes: 3833. Organization: alibaba. License: Apache 2.0.

61.5% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,282 - 1,302

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #35 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 53.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: humor. Source rank: #40. Votes: 1178. Organization: alibaba. License: Apache 2.0.

53.4% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,244 - 1,279

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #44 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 57%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: ocr. Source rank: #48. Votes: 21841. Organization: alibaba. License: Apache 2.0.

57% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,266 - 1,277

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #58 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 83.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #61. Votes: 6096. Organization: alibaba. License: Apache 2.0.

83.8% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,490 - 1,506

Text Arena · French

AR · Multilingual · Human

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

Rank #67 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 74.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: french. Source rank: #75. Votes: 2840. Organization: alibaba. License: Apache 2.0.

74.3% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,456 - 1,482

Text Arena · German

AR · Multilingual · Human

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

Rank #66 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 76.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: german. Source rank: #75. Votes: 1364. Organization: alibaba. License: Apache 2.0.

76.1% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,429 - 1,463

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #50 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 79.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: japanese. Source rank: #56. Votes: 1032. Organization: alibaba. License: Apache 2.0.

79.8% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,409 - 1,449

Text Arena · Korean

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 67.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: korean. Source rank: #93. Votes: 1478. Organization: alibaba. License: Apache 2.0.

67.2% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,366 - 1,400

Text Arena · Non English

AR · Multilingual · Human

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

Rank #82 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 78.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: non_english. Source rank: #90. Votes: 49373. Organization: alibaba. License: Apache 2.0.

78.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,435

Text Arena · Polish

AR · Multilingual · Human

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

Rank #57 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 71.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: polish. Source rank: #68. Votes: 1583. Organization: alibaba. License: Apache 2.0.

71.9% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,434 - 1,464

Text Arena · Russian

AR · Multilingual · Human

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

Rank #87 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 74.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: russian. Source rank: #97. Votes: 10116. Organization: alibaba. License: Apache 2.0.

74.8% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,428 - 1,441

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #73 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 72.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: spanish. Source rank: #81. Votes: 2727. Organization: alibaba. License: Apache 2.0.

72.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,428 - 1,453

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #49 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 86.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #52. Votes: 6096. Organization: alibaba. License: Apache 2.0.

86.4% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,492 - 1,508

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #47 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 82.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: french. Source rank: #51. Votes: 2840. Organization: alibaba. License: Apache 2.0.

82.1% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,449 - 1,475

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #48 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 82.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: german. Source rank: #52. Votes: 1364. Organization: alibaba. License: Apache 2.0.

82.7% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,431 - 1,465

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #36 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 85.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: japanese. Source rank: #39. Votes: 1032. Organization: alibaba. License: Apache 2.0.

85.6% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,407 - 1,447

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 68%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: korean. Source rank: #88. Votes: 1478. Organization: alibaba. License: Apache 2.0.

68% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,365 - 1,399

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: non_english. Source rank: #74. Votes: 49373. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,426 - 1,434

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #40 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 80.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: polish. Source rank: #44. Votes: 1583. Organization: alibaba. License: Apache 2.0.

80.4% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,437 - 1,467

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #78 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: russian. Source rank: #84. Votes: 10116. Organization: alibaba. License: Apache 2.0.

77.4% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,422 - 1,435

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #69 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 73.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: spanish. Source rank: #74. Votes: 2727. Organization: alibaba. License: Apache 2.0.

73.7% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,430 - 1,455

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #42 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 60.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #46. Votes: 1985. Organization: alibaba. License: Apache 2.0.

60.6% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,276 - 1,308

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #36 · Source label: qwen3.5-397b-a17b

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 66.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3.5-397b-a17b`. Category: chinese. Source rank: #40. Votes: 1985. Organization: alibaba. License: Apache 2.0.

66.3% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,299 - 1,330

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

Qwen3.5 397B A17B

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

Qwen3.5 397B A17B

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks