Model profile · Qwen

Qwen3 Max

Open weightsfrontier · registry tag 2026 hosted frontier

Thin verified coverage

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

Visible coverage: 17.8%
Verified coverage: 17.8%
Spread: n/a
Last verified: Oct 3, 2026

textcodevisiondocument5 aliases30 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 #249 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13
Percentile: 55.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

55.3% percentile inside its fair comparison set

13Raw 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 #174 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.2%
Percentile: 61.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

61.8% percentile inside its fair comparison set

24.2%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 #330 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.1%
Percentile: 27.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

27.4% percentile inside its fair comparison set

10.1%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 #149 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.1%
Percentile: 57.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

57.5% percentile inside its fair comparison set

44.1%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 #232 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.2 /1M input tokens
Percentile: 34.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

34.7% percentile inside its fair comparison set

$1.2 /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 #253 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $6 /1M output tokens
Percentile: 30.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

30.5% percentile inside its fair comparison set

$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 #195 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.2 tokens/s
Percentile: 26%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

26% percentile inside its fair comparison set

58.2 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 #167 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.00s
Percentile: 37.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

37.1% percentile inside its fair comparison set

4.00sRaw 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 #68 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.00s
Percentile: 74.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

74.4% percentile inside its fair comparison set

4.00sRaw 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 #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 75.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: overall. Source rank: #106. Votes: 27232. Organization: alibaba. License: Proprietary.

75.3% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,430 - 1,439

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 #108 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 71.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: creative_writing. Source rank: #118. Votes: 3687. Organization: alibaba. License: Proprietary.

71.4% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,383 - 1,404

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 #101 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 73.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: english. Source rank: #111. Votes: 11441. Organization: alibaba. License: Proprietary.

73.4% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,434 - 1,446

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 #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 75.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: exclude_ties. Source rank: #105. Votes: 19326. Organization: alibaba. License: Proprietary.

75.3% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,425 - 1,438

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 #92 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 75.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts. Source rank: #102. Votes: 13493. Organization: alibaba. License: Proprietary.

75.8% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,453 - 1,464

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 #96 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 74.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts_english. Source rank: #106. Votes: 5802. Organization: alibaba. License: Proprietary.

74.6% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,452 - 1,468

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 #95 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: instruction_following. Source rank: #105. Votes: 7256. Organization: alibaba. License: Proprietary.

75% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,417 - 1,432

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 #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 73.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: longer_query. Source rank: #103. Votes: 6126. Organization: alibaba. License: Proprietary.

73.8% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,435 - 1,451

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 #86 · Source label: qwen3-max-2025-09-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 77.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-2025-09-23`. Category: multi_turn. Source rank: #96. Votes: 1636. Organization: alibaba. License: Proprietary.

77.3% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,432 - 1,461

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 #71 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 81.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: overall. Source rank: #77. Votes: 27232. Organization: alibaba. License: Proprietary.

81.4% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,434 - 1,444

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 #85 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 77.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: creative_writing. Source rank: #94. Votes: 3687. Organization: alibaba. License: Proprietary.

77.5% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,392 - 1,411

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 #83 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: english. Source rank: #89. Votes: 11441. Organization: alibaba. License: Proprietary.

78.2% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,436 - 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 #69 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: exclude_ties. Source rank: #75. Votes: 19326. Organization: alibaba. License: Proprietary.

81.9% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,430 - 1,442

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 #73 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts. Source rank: #76. Votes: 13493. Organization: alibaba. License: Proprietary.

80.9% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,442 - 1,454

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 #84 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 77.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts_english. Source rank: #87. Votes: 5802. Organization: alibaba. License: Proprietary.

77.8% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 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 #81 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 78.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: instruction_following. Source rank: #86. Votes: 7256. Organization: alibaba. License: Proprietary.

78.7% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,412 - 1,427

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 #75 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 79.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: longer_query. Source rank: #79. Votes: 6126. Organization: alibaba. License: Proprietary.

79.2% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,431 - 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 #67 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 82.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: multi_turn. Source rank: #73. Votes: 4527. Organization: alibaba. License: Proprietary.

82.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,437 - 1,455

Coding5 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 #109 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 19.7%
Percentile: 67.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

67.5% percentile inside its fair comparison set

19.7%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 #98 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: coding. Source rank: #108. Votes: 5337. Organization: alibaba. License: Proprietary.

73.9% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,472 - 1,489

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 #82 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: coding. Source rank: #87. Votes: 5337. Organization: alibaba. License: Proprietary.

78.2% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,447 - 1,464

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #86 · Source label: alibaba/qwen3-max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 3.5%
Percentile: 8.6%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Alibaba.

8.6% percentile inside its fair comparison set

3.5%Raw benchmark valueCI 1% - 6%

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #74 · Source label: alibaba/qwen3-max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.2%
Percentile: 41.6%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Alibaba.

41.6% percentile inside its fair comparison set

78.2%Raw benchmark valueCI 76% - 80.4%

Reasoning / math / science7 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 #235 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.1%
Percentile: 55.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

55.8% percentile inside its fair comparison set

10.1%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 #167 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.4%
Percentile: 66.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

66.5% percentile inside its fair comparison set

76.4%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 #249 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 50.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

50.1% percentile inside its fair comparison set

0%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 #92 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 74.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: math. Source rank: #99. Votes: 1488. Organization: alibaba. License: Proprietary.

74.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,419 - 1,449

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 #66 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: math. Source rank: #70. Votes: 1488. Organization: alibaba. License: Proprietary.

81.9% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,432 - 1,462

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

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

Rank #51 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.8%
Percentile: 60.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Alibaba.

60.5% percentile inside its fair comparison set

84.8%Raw benchmark valueCI 81.3% - 88.4%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #60 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85%
Percentile: 52.8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Alibaba.

52.8% percentile inside its fair comparison set

85%Raw benchmark valueCI 84.3% - 85.7%

Professional reasoning23 benchmarksn/a

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #90 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 72.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: expert. Source rank: #97. Votes: 1323. Organization: alibaba. License: Proprietary.

72.8% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,448 - 1,481

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 #80 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 78.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_business_and_management_and_financial_operations. Source rank: #88. Votes: 5125. Organization: alibaba. License: Proprietary.

78.6% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,436 - 1,454

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 #102 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 73%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #114. Votes: 4917. Organization: alibaba. License: Proprietary.

73% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,388 - 1,406

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #111 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 68.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_legal_and_government. Source rank: #125. Votes: 1687. Organization: alibaba. License: Proprietary.

68.5% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,416 - 1,445

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 #88 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 76.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #96. Votes: 4198. Organization: alibaba. License: Proprietary.

76.7% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,447 - 1,466

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #100 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 72.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_mathematical. Source rank: #108. Votes: 1309. Organization: alibaba. License: Proprietary.

72.2% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,420 - 1,452

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #63 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 82.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_medicine_and_healthcare. Source rank: #69. Votes: 1463. Organization: alibaba. License: Proprietary.

82.1% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,458 - 1,490

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 #97 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 74.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_software_and_it_services. Source rank: #107. Votes: 9302. Organization: alibaba. License: Proprietary.

74.5% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,463 - 1,477

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 #103 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_writing_and_literature_and_language. Source rank: #116. Votes: 6130. Organization: alibaba. License: Proprietary.

72.8% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,398 - 1,413

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #72 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 78.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: expert. Source rank: #75. Votes: 1323. Organization: alibaba. License: Proprietary.

78.3% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,441 - 1,473

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 #58 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 84.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_business_and_management_and_financial_operations. Source rank: #61. Votes: 5125. Organization: alibaba. License: Proprietary.

84.6% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,428 - 1,445

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 #78 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #85. Votes: 4917. Organization: alibaba. License: Proprietary.

79.4% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,395 - 1,413

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 #92 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_legal_and_government. Source rank: #99. Votes: 1687. Organization: alibaba. License: Proprietary.

73.9% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,420 - 1,448

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 #63 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 83.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #66. Votes: 4198. Organization: alibaba. License: Proprietary.

83.4% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,448 - 1,467

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #76 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 78.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_mathematical. Source rank: #79. Votes: 1309. Organization: alibaba. License: Proprietary.

78.9% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,429 - 1,461

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 #38 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 89.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_medicine_and_healthcare. Source rank: #39. Votes: 1463. Organization: alibaba. License: Proprietary.

89.3% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,452 - 1,484

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 #79 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 79.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_software_and_it_services. Source rank: #83. Votes: 9302. Organization: alibaba. License: Proprietary.

79.3% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,452 - 1,465

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 #93 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 75.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_writing_and_literature_and_language. Source rank: #101. Votes: 6130. Organization: alibaba. License: Proprietary.

75.5% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,399 - 1,415

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #76 · Source label: alibaba/qwen3-max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.9%
Percentile: 44.4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Alibaba.

44.4% percentile inside its fair comparison set

81.9%Raw benchmark valueCI 81.1% - 82.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #89 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31.4%
Percentile: 7.4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Alibaba.

7.4% percentile inside its fair comparison set

31.4%Raw benchmark valueCI 27.7% - 35.1%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #76 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.7%
Percentile: 21.9%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Alibaba.

21.9% percentile inside its fair comparison set

72.7%Raw benchmark valueCI 69% - 76.4%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #43 · Source label: alibaba/qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74%
Percentile: 67.4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

67.4% percentile inside its fair comparison set

74%Raw benchmark valueCI 72.3% - 75.6%

Poker Agent

VALS-AI · Professional reasoning · Objective

Agent profit in poker-style strategic play.

Rank #18 · Source label: alibaba/qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 994.5 score
Percentile: 10.5%
Last updated: archived
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: poker_agent; provider: unknown.

10.5% percentile inside its fair comparison set

994.5 scoreRaw benchmark valueCI 994.5 score - 994.5 score

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 #179 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.7%
Percentile: 47.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

47.5% percentile inside its fair comparison set

32.7%Raw benchmark value

Long context2 benchmarksn/a

Long Context Reasoning

AA · Long context · Objective

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

Rank #253 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 44.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

44.6% percentile inside its fair comparison set

43%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

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

Rank #12 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68%
Percentile: 90.6%
Last updated: aging
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Alibaba.

90.6% percentile inside its fair comparison set

68%Raw benchmark valueCI 66.2% - 69.8%

Multilingual18 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #85 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 76.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: chinese. Source rank: #92. Votes: 2064. Organization: alibaba. License: Proprietary.

76.1% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,466 - 1,492

Text Arena · French

AR · Multilingual · Human

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

Rank #85 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 67.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: french. Source rank: #96. Votes: 433. Organization: alibaba. License: Proprietary.

67.3% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,422 - 1,480

Text Arena · German

AR · Multilingual · Human

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

Rank #61 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: german. Source rank: #69. Votes: 595. Organization: alibaba. License: Proprietary.

77.9% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,424 - 1,474

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #84 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 65.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: japanese. Source rank: #98. Votes: 432. Organization: alibaba. License: Proprietary.

65.8% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,357 - 1,415

Text Arena · Korean

AR · Multilingual · Human

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

Rank #77 · Source label: qwen3-max-2025-09-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 68.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-2025-09-23`. Category: korean. Source rank: #87. Votes: 254. Organization: alibaba. License: Proprietary.

68.9% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,350 - 1,424

Text Arena · Non English

AR · Multilingual · Human

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

Rank #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 75.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: non_english. Source rank: #106. Votes: 15710. Organization: alibaba. License: Proprietary.

75.3% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,417 - 1,428

Text Arena · Polish

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 59.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: polish. Source rank: #94. Votes: 1452. Organization: alibaba. License: Proprietary.

59.8% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,411 - 1,443

Text Arena · Russian

AR · Multilingual · Human

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

Rank #92 · Source label: qwen3-max-2025-09-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 73.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-2025-09-23`. Category: russian. Source rank: #104. Votes: 719. Organization: alibaba. License: Proprietary.

73.3% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,409 - 1,452

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #58 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 78%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: spanish. Source rank: #64. Votes: 844. Organization: alibaba. License: Proprietary.

78% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,431 - 1,472

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #70 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 80.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: chinese. Source rank: #73. Votes: 2064. Organization: alibaba. License: Proprietary.

80.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,467 - 1,493

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #72 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 72.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: french. Source rank: #77. Votes: 433. Organization: alibaba. License: Proprietary.

72.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,421 - 1,479

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #34 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 87.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: german. Source rank: #36. Votes: 595. Organization: alibaba. License: Proprietary.

87.9% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,438 - 1,488

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 73.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: japanese. Source rank: #73. Votes: 432. Organization: alibaba. License: Proprietary.

73.7% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,371 - 1,428

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #62 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: korean. Source rank: #68. Votes: 701. Organization: alibaba. License: Proprietary.

75% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,374 - 1,421

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #69 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: non_english. Source rank: #75. Votes: 15710. Organization: alibaba. License: Proprietary.

81.9% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,424 - 1,435

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #53 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: polish. Source rank: #59. Votes: 1452. Organization: alibaba. License: Proprietary.

73.9% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,424 - 1,456

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: russian. Source rank: #85. Votes: 1856. Organization: alibaba. License: Proprietary.

77.1% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,414 - 1,441

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 86.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: spanish. Source rank: #36. Votes: 844. Organization: alibaba. License: Proprietary.

86.9% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,442 - 1,483

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

Artificial Analysis

Oct 3, 2026

source →

Model profile · Qwen

Qwen3 Max

Open weightsfrontier · registry tag 2026 hosted frontier

Thin verified coverage

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

Visible coverage: 17.8%
Verified coverage: 17.8%
Spread: n/a
Last verified: Oct 3, 2026

textcodevisiondocument5 aliases30 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 #249 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13
Percentile: 55.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

55.3% percentile inside its fair comparison set

13Raw 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 #174 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.2%
Percentile: 61.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

61.8% percentile inside its fair comparison set

24.2%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 #330 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.1%
Percentile: 27.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

27.4% percentile inside its fair comparison set

10.1%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 #149 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.1%
Percentile: 57.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

57.5% percentile inside its fair comparison set

44.1%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 #232 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.2 /1M input tokens
Percentile: 34.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

34.7% percentile inside its fair comparison set

$1.2 /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 #253 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $6 /1M output tokens
Percentile: 30.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

30.5% percentile inside its fair comparison set

$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 #195 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.2 tokens/s
Percentile: 26%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

26% percentile inside its fair comparison set

58.2 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 #167 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.00s
Percentile: 37.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

37.1% percentile inside its fair comparison set

4.00sRaw 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 #68 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.00s
Percentile: 74.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

74.4% percentile inside its fair comparison set

4.00sRaw 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 #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 75.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: overall. Source rank: #106. Votes: 27232. Organization: alibaba. License: Proprietary.

75.3% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,430 - 1,439

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 #108 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 71.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: creative_writing. Source rank: #118. Votes: 3687. Organization: alibaba. License: Proprietary.

71.4% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,383 - 1,404

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 #101 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 73.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: english. Source rank: #111. Votes: 11441. Organization: alibaba. License: Proprietary.

73.4% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,434 - 1,446

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 #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 75.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: exclude_ties. Source rank: #105. Votes: 19326. Organization: alibaba. License: Proprietary.

75.3% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,425 - 1,438

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 #92 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 75.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts. Source rank: #102. Votes: 13493. Organization: alibaba. License: Proprietary.

75.8% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,453 - 1,464

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 #96 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 74.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts_english. Source rank: #106. Votes: 5802. Organization: alibaba. License: Proprietary.

74.6% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,452 - 1,468

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 #95 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: instruction_following. Source rank: #105. Votes: 7256. Organization: alibaba. License: Proprietary.

75% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,417 - 1,432

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 #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 73.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: longer_query. Source rank: #103. Votes: 6126. Organization: alibaba. License: Proprietary.

73.8% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,435 - 1,451

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 #86 · Source label: qwen3-max-2025-09-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 77.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-2025-09-23`. Category: multi_turn. Source rank: #96. Votes: 1636. Organization: alibaba. License: Proprietary.

77.3% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,432 - 1,461

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 #71 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 81.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: overall. Source rank: #77. Votes: 27232. Organization: alibaba. License: Proprietary.

81.4% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,434 - 1,444

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 #85 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 77.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: creative_writing. Source rank: #94. Votes: 3687. Organization: alibaba. License: Proprietary.

77.5% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,392 - 1,411

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 #83 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: english. Source rank: #89. Votes: 11441. Organization: alibaba. License: Proprietary.

78.2% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,436 - 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 #69 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: exclude_ties. Source rank: #75. Votes: 19326. Organization: alibaba. License: Proprietary.

81.9% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,430 - 1,442

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 #73 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts. Source rank: #76. Votes: 13493. Organization: alibaba. License: Proprietary.

80.9% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,442 - 1,454

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 #84 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 77.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: hard_prompts_english. Source rank: #87. Votes: 5802. Organization: alibaba. License: Proprietary.

77.8% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 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 #81 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 78.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: instruction_following. Source rank: #86. Votes: 7256. Organization: alibaba. License: Proprietary.

78.7% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,412 - 1,427

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 #75 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 79.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: longer_query. Source rank: #79. Votes: 6126. Organization: alibaba. License: Proprietary.

79.2% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,431 - 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 #67 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 82.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: multi_turn. Source rank: #73. Votes: 4527. Organization: alibaba. License: Proprietary.

82.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,437 - 1,455

Coding5 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 #109 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 19.7%
Percentile: 67.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

67.5% percentile inside its fair comparison set

19.7%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 #98 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: coding. Source rank: #108. Votes: 5337. Organization: alibaba. License: Proprietary.

73.9% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,472 - 1,489

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 #82 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 78.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: coding. Source rank: #87. Votes: 5337. Organization: alibaba. License: Proprietary.

78.2% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,447 - 1,464

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #86 · Source label: alibaba/qwen3-max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 3.5%
Percentile: 8.6%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Alibaba.

8.6% percentile inside its fair comparison set

3.5%Raw benchmark valueCI 1% - 6%

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #74 · Source label: alibaba/qwen3-max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.2%
Percentile: 41.6%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Alibaba.

41.6% percentile inside its fair comparison set

78.2%Raw benchmark valueCI 76% - 80.4%

Reasoning / math / science7 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 #235 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.1%
Percentile: 55.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

55.8% percentile inside its fair comparison set

10.1%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 #167 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.4%
Percentile: 66.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

66.5% percentile inside its fair comparison set

76.4%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 #249 · Source label: Qwen3 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 50.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

50.1% percentile inside its fair comparison set

0%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 #92 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 74.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: math. Source rank: #99. Votes: 1488. Organization: alibaba. License: Proprietary.

74.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,419 - 1,449

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 #66 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: math. Source rank: #70. Votes: 1488. Organization: alibaba. License: Proprietary.

81.9% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,432 - 1,462

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

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

Rank #51 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.8%
Percentile: 60.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Alibaba.

60.5% percentile inside its fair comparison set

84.8%Raw benchmark valueCI 81.3% - 88.4%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #60 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85%
Percentile: 52.8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Alibaba.

52.8% percentile inside its fair comparison set

85%Raw benchmark valueCI 84.3% - 85.7%

Professional reasoning23 benchmarksn/a

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #90 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 72.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: expert. Source rank: #97. Votes: 1323. Organization: alibaba. License: Proprietary.

72.8% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,448 - 1,481

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 #80 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 78.6%
Last updated: recent
Eligibility: preview_model

78.6% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,436 - 1,454

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 #102 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 73%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #114. Votes: 4917. Organization: alibaba. License: Proprietary.

73% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,388 - 1,406

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #111 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 68.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_legal_and_government. Source rank: #125. Votes: 1687. Organization: alibaba. License: Proprietary.

68.5% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,416 - 1,445

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 #88 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 76.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #96. Votes: 4198. Organization: alibaba. License: Proprietary.

76.7% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,447 - 1,466

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #100 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 72.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_mathematical. Source rank: #108. Votes: 1309. Organization: alibaba. License: Proprietary.

72.2% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,420 - 1,452

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #63 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 82.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_medicine_and_healthcare. Source rank: #69. Votes: 1463. Organization: alibaba. License: Proprietary.

82.1% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,458 - 1,490

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 #97 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 74.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_software_and_it_services. Source rank: #107. Votes: 9302. Organization: alibaba. License: Proprietary.

74.5% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,463 - 1,477

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 #103 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_writing_and_literature_and_language. Source rank: #116. Votes: 6130. Organization: alibaba. License: Proprietary.

72.8% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,398 - 1,413

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #72 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 78.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: expert. Source rank: #75. Votes: 1323. Organization: alibaba. License: Proprietary.

78.3% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,441 - 1,473

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 #58 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 84.6%
Last updated: recent
Eligibility: preview_model

84.6% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,428 - 1,445

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 #78 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 79.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #85. Votes: 4917. Organization: alibaba. License: Proprietary.

79.4% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,395 - 1,413

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 #92 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_legal_and_government. Source rank: #99. Votes: 1687. Organization: alibaba. License: Proprietary.

73.9% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,420 - 1,448

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 #63 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 83.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #66. Votes: 4198. Organization: alibaba. License: Proprietary.

83.4% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,448 - 1,467

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #76 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 78.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_mathematical. Source rank: #79. Votes: 1309. Organization: alibaba. License: Proprietary.

78.9% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,429 - 1,461

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 #38 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 89.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_medicine_and_healthcare. Source rank: #39. Votes: 1463. Organization: alibaba. License: Proprietary.

89.3% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,452 - 1,484

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 #79 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 79.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_software_and_it_services. Source rank: #83. Votes: 9302. Organization: alibaba. License: Proprietary.

79.3% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,452 - 1,465

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 #93 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 75.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: industry_writing_and_literature_and_language. Source rank: #101. Votes: 6130. Organization: alibaba. License: Proprietary.

75.5% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,399 - 1,415

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #76 · Source label: alibaba/qwen3-max

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.9%
Percentile: 44.4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Alibaba.

44.4% percentile inside its fair comparison set

81.9%Raw benchmark valueCI 81.1% - 82.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #89 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31.4%
Percentile: 7.4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Alibaba.

7.4% percentile inside its fair comparison set

31.4%Raw benchmark valueCI 27.7% - 35.1%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #76 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.7%
Percentile: 21.9%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Alibaba.

21.9% percentile inside its fair comparison set

72.7%Raw benchmark valueCI 69% - 76.4%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #43 · Source label: alibaba/qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74%
Percentile: 67.4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

67.4% percentile inside its fair comparison set

74%Raw benchmark valueCI 72.3% - 75.6%

Poker Agent

VALS-AI · Professional reasoning · Objective

Agent profit in poker-style strategic play.

Rank #18 · Source label: alibaba/qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 994.5 score
Percentile: 10.5%
Last updated: archived
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: poker_agent; provider: unknown.

10.5% percentile inside its fair comparison set

994.5 scoreRaw benchmark valueCI 994.5 score - 994.5 score

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 #179 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.7%
Percentile: 47.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

47.5% percentile inside its fair comparison set

32.7%Raw benchmark value

Long context2 benchmarksn/a

Long Context Reasoning

AA · Long context · Objective

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

Rank #253 · Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 44.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

44.6% percentile inside its fair comparison set

43%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

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

Rank #12 · Source label: alibaba/qwen3-max-2026-01-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68%
Percentile: 90.6%
Last updated: aging
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Alibaba.

90.6% percentile inside its fair comparison set

68%Raw benchmark valueCI 66.2% - 69.8%

Multilingual18 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #85 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 76.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: chinese. Source rank: #92. Votes: 2064. Organization: alibaba. License: Proprietary.

76.1% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,466 - 1,492

Text Arena · French

AR · Multilingual · Human

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

Rank #85 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 67.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: french. Source rank: #96. Votes: 433. Organization: alibaba. License: Proprietary.

67.3% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,422 - 1,480

Text Arena · German

AR · Multilingual · Human

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

Rank #61 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 77.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: german. Source rank: #69. Votes: 595. Organization: alibaba. License: Proprietary.

77.9% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,424 - 1,474

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #84 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 65.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: japanese. Source rank: #98. Votes: 432. Organization: alibaba. License: Proprietary.

65.8% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,357 - 1,415

Text Arena · Korean

AR · Multilingual · Human

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

Rank #77 · Source label: qwen3-max-2025-09-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 68.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-2025-09-23`. Category: korean. Source rank: #87. Votes: 254. Organization: alibaba. License: Proprietary.

68.9% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,350 - 1,424

Text Arena · Non English

AR · Multilingual · Human

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

Rank #94 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 75.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: non_english. Source rank: #106. Votes: 15710. Organization: alibaba. License: Proprietary.

75.3% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,417 - 1,428

Text Arena · Polish

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 59.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: polish. Source rank: #94. Votes: 1452. Organization: alibaba. License: Proprietary.

59.8% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,411 - 1,443

Text Arena · Russian

AR · Multilingual · Human

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

Rank #92 · Source label: qwen3-max-2025-09-23

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 73.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-2025-09-23`. Category: russian. Source rank: #104. Votes: 719. Organization: alibaba. License: Proprietary.

73.3% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,409 - 1,452

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #58 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 78%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: spanish. Source rank: #64. Votes: 844. Organization: alibaba. License: Proprietary.

78% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,431 - 1,472

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #70 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 80.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: chinese. Source rank: #73. Votes: 2064. Organization: alibaba. License: Proprietary.

80.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,467 - 1,493

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #72 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 72.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: french. Source rank: #77. Votes: 433. Organization: alibaba. License: Proprietary.

72.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,421 - 1,479

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #34 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 87.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: german. Source rank: #36. Votes: 595. Organization: alibaba. License: Proprietary.

87.9% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,438 - 1,488

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 73.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: japanese. Source rank: #73. Votes: 432. Organization: alibaba. License: Proprietary.

73.7% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,371 - 1,428

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #62 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: korean. Source rank: #68. Votes: 701. Organization: alibaba. License: Proprietary.

75% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,374 - 1,421

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #69 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 81.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: non_english. Source rank: #75. Votes: 15710. Organization: alibaba. License: Proprietary.

81.9% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,424 - 1,435

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #53 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: polish. Source rank: #59. Votes: 1452. Organization: alibaba. License: Proprietary.

73.9% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,424 - 1,456

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: russian. Source rank: #85. Votes: 1856. Organization: alibaba. License: Proprietary.

77.1% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,414 - 1,441

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 86.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `qwen3-max-preview`. Category: spanish. Source rank: #36. Votes: 844. Organization: alibaba. License: Proprietary.

86.9% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,442 - 1,483

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

Artificial Analysis

Oct 3, 2026

source →

Qwen3 Max

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

Qwen3 Max

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks