Model profile · Qwen

qwen3.8-27b

Open weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

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

Visible coverage: 47.3%
Verified coverage: 47.3%
Spread: 96.9%
Last verified: Oct 3, 2026

66%capability fit

textcodevisiondocument3 aliases43 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text35 benchmarks68.5%

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 #76 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 34
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

86.5% percentile inside its fair comparison set

34Raw 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 #314 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.6%
Percentile: 30.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

30.9% percentile inside its fair comparison set

15.6%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 #33 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.7%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

92.9% percentile inside its fair comparison set

69.7%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 #186 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.5 /1M input tokens
Percentile: 49.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

49.7% percentile inside its fair comparison set

$0.5 /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 #207 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3 /1M output tokens
Percentile: 44.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

44.1% percentile inside its fair comparison set

$3 /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 #230 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.1 tokens/s
Percentile: 12.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

12.6% percentile inside its fair comparison set

46.1 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 #166 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.92s
Percentile: 37.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

37.5% percentile inside its fair comparison set

3.92sRaw 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 #214 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.29s
Percentile: 18.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

18.7% percentile inside its fair comparison set

47.29sRaw 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 #90 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #99. Votes: 18462. Organization: alibaba. License: Apache 2.0.

76.3% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,432 - 1,443

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 #144 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing. Source rank: #163. Votes: 3654. Organization: alibaba. License: Apache 2.0.

61.8% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,353 - 1,374

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 #103 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #113. Votes: 7018. Organization: alibaba. License: Apache 2.0.

72.9% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,432 - 1,447

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 76.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: exclude_ties. Source rank: #101. Votes: 13519. Organization: alibaba. License: Apache 2.0.

76.1% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,426 - 1,440

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 #81 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 78.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts. Source rank: #89. Votes: 12126. Organization: alibaba. License: Apache 2.0.

78.7% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,457 - 1,470

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 #103 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 72.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts_english. Source rank: #114. Votes: 4669. Organization: alibaba. License: Apache 2.0.

72.7% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,448 - 1,466

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 76.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: instruction_following. Source rank: #101. Votes: 6537. Organization: alibaba. License: Apache 2.0.

76.1% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,418 - 1,434

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 74.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: longer_query. Source rank: #100. Votes: 8253. Organization: alibaba. License: Apache 2.0.

74.6% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,437 - 1,452

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 75.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: multi_turn. Source rank: #103. Votes: 2983. Organization: alibaba. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,431 - 1,453

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 #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #74. Votes: 18462. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,435 - 1,446

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 #118 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing. Source rank: #128. Votes: 3654. Organization: alibaba. License: Apache 2.0.

68.7% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,370 - 1,391

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 #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 80.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #81. Votes: 7018. Organization: alibaba. License: Apache 2.0.

80.1% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,439 - 1,454

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 #70 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 81.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: exclude_ties. Source rank: #76. Votes: 13519. Organization: alibaba. License: Apache 2.0.

81.6% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,428 - 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 #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts. Source rank: #57. Votes: 12126. Organization: alibaba. License: Apache 2.0.

85.9% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,455 - 1,467

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 #63 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts_english. Source rank: #66. Votes: 4669. Organization: alibaba. License: Apache 2.0.

83.4% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,451 - 1,469

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 #58 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: instruction_following. Source rank: #61. Votes: 6537. Organization: alibaba. License: Apache 2.0.

84.8% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,430 - 1,446

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 #61 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: longer_query. Source rank: #64. Votes: 8253. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,441 - 1,456

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 #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 79.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: multi_turn. Source rank: #83. Votes: 2983. Organization: alibaba. License: Apache 2.0.

79.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,431 - 1,453

Instruction following

LB · Chat / text · Objective

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

Rank #18 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.7%
Percentile: 73.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

73.8% percentile inside its fair comparison set

72.7%Raw benchmark value

Language

LB · Chat / text · Objective

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.3%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

21.5% percentile inside its fair comparison set

74.3%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #12 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.9%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

83.1% percentile inside its fair comparison set

74.9%Raw benchmark value

Simplify

LB · Chat / text · Objective

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

Rank #25 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.7%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

63.1% percentile inside its fair comparison set

66.7%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #27 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.1%
Percentile: 60%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

60% percentile inside its fair comparison set

73.1%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #17 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.9%
Percentile: 75.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

75.4% percentile inside its fair comparison set

75.9%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #59 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.5%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

12.3% percentile inside its fair comparison set

90.5%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

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

Rank #46 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 56.5%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

30.8% percentile inside its fair comparison set

56.5%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76%
Percentile: 24.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

24.6% percentile inside its fair comparison set

76%Raw benchmark value

Coding21 benchmarks58.5%

SciCode

AA · Coding · Objective

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

Rank #105 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.6%
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

47.5% percentile inside its fair comparison set

46.6%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 #67 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: coding. Source rank: #73. Votes: 5208. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,493 - 1,511

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 #43 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 88.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: coding. Source rank: #44. Votes: 5208. Organization: alibaba. License: Apache 2.0.

88.7% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,477 - 1,494

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 #36 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.9%
Percentile: 62.4%
Last updated: recent
Eligibility: headline eligible

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

62.4% percentile inside its fair comparison set

64.9%Raw benchmark valueCI 55.4% - 74.3%

WebDev Arena

AR · Coding · Human

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

Rank #27 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,591
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #28. Votes: 12388. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,591Raw benchmark valueCI 1,584 - 1,598

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #27 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,576
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: webdev-html. Source rank: #28. Votes: 1877. Organization: alibaba. License: Apache 2.0.

79.2% percentile inside its fair comparison set

1,576Raw benchmark valueCI 1,561 - 1,591

Code Arena · Webdev React

AR · Coding · Human

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

Rank #26 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,599
Percentile: 77.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: webdev-react. Source rank: #27. Votes: 8107. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,599Raw benchmark valueCI 1,591 - 1,607

Code Migration

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 #51 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 14.2%
Percentile: 26.5%
Last updated: recent
Eligibility: headline eligible

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

26.5% percentile inside its fair comparison set

14.2%Raw benchmark valueCI 5.9% - 22.4%

IOI

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 #31 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 39.1%
Percentile: 18.9%
Last updated: recent
Eligibility: headline eligible

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

18.9% percentile inside its fair comparison set

39.1%Raw benchmark valueCI 29.4% - 48.7%

ProgramBench

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 #46 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

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

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Terminal-Bench 2.1

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 #39 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58.4%
Percentile: 43.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

43.3% percentile inside its fair comparison set

58.4%Raw benchmark valueCI 48.1% - 68.7%

Code Arena · Image To Webdev

AR · Coding · Human

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

Rank #10 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,582
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: image_to_webdev. Source rank: #11. Votes: 2439. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,582Raw benchmark valueCI 1,570 - 1,595

SWE-bench Verified

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 #15 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86%
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

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

82.9% percentile inside its fair comparison set

86%Raw benchmark valueCI 83% - 89%

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 #41 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84%
Percentile: 68%
Last updated: recent
Eligibility: headline eligible

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

68% percentile inside its fair comparison set

84%Raw benchmark valueCI 82% - 86%

Agentic coding

LB · Coding · Objective

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

Rank #13 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.4%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

81.5% percentile inside its fair comparison set

61.4%Raw benchmark value

Coding

LB · Coding · Objective

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

Rank #47 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.7%
Percentile: 29.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

29.2% percentile inside its fair comparison set

75.7%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #57 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 59.1%
Percentile: 27.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

27.7% percentile inside its fair comparison set

59.1%Raw benchmark value

TypeScript

LB · Coding · Objective

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

Rank #16 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

81.5% percentile inside its fair comparison set

50%Raw benchmark value

Python

LB · Coding · Objective

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

Rank #3 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

98.5% percentile inside its fair comparison set

75%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #34 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77.5%
Percentile: 52.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

52.3% percentile inside its fair comparison set

77.5%Raw benchmark value

Coding completion

LB · Coding · Objective

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.9%
Percentile: 24.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

24.6% percentile inside its fair comparison set

73.9%Raw benchmark value

Reasoning / math / science18 benchmarks54.8%

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 #90 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.9%
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

83.2% percentile inside its fair comparison set

33.9%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 #42 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 90.5%
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

91.9% percentile inside its fair comparison set

90.5%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 #102 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.4%
Percentile: 78.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

78.3% percentile inside its fair comparison set

5.4%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 #63 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: math. Source rank: #66. Votes: 897. Organization: alibaba. License: Apache 2.0.

82.7% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,437 - 1,476

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 #51 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: math. Source rank: #53. Votes: 897. Organization: alibaba. License: Apache 2.0.

86.1% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,440 - 1,479

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #39 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 16%
Percentile: 14.3%
Last updated: recent
Eligibility: headline eligible

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

14.3% percentile inside its fair comparison set

16%Raw benchmark valueCI 8.8% - 23.2%

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 #33 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.9%
Percentile: 75%
Last updated: recent
Eligibility: headline eligible

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

75% percentile inside its fair comparison set

88.9%Raw benchmark valueCI 85.8% - 92%

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 #64 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.3%
Percentile: 49.6%
Last updated: recent
Eligibility: headline eligible

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

49.6% percentile inside its fair comparison set

84.3%Raw benchmark valueCI 83.6% - 85%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #50 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.2%
Percentile: 24.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

24.6% percentile inside its fair comparison set

86.2%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #51 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

23.1% percentile inside its fair comparison set

80%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

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

Rank #33 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

83.1% percentile inside its fair comparison set

98%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #50 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

26.2% percentile inside its fair comparison set

65%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

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

Rank #57 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.1%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

26.2% percentile inside its fair comparison set

94.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #51 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.7%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

23.1% percentile inside its fair comparison set

87.7%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 59.6%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

1.5% percentile inside its fair comparison set

59.6%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #30 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.5%
Percentile: 55.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

55.4% percentile inside its fair comparison set

96.5%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #48 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

41.5% percentile inside its fair comparison set

96%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

Rank #50 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

30.8% percentile inside its fair comparison set

68%Raw benchmark value

Professional reasoning32 benchmarks47.3%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #75 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: expert. Source rank: #80. Votes: 2018. Organization: alibaba. License: Apache 2.0.

77.4% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,462 - 1,489

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 #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 74.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_business_and_management_and_financial_operations. Source rank: #107. Votes: 3457. Organization: alibaba. License: Apache 2.0.

74.5% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,426 - 1,447

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 #124 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 67.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_entertainment_and_sports_and_media. Source rank: #139. Votes: 4557. Organization: alibaba. License: Apache 2.0.

67.1% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,373 - 1,392

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 73.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_legal_and_government. Source rank: #108. Votes: 1417. Organization: alibaba. License: Apache 2.0.

73.1% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,423 - 1,456

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 #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 79.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_life_and_physical_and_social_science. Source rank: #83. Votes: 2904. Organization: alibaba. License: Apache 2.0.

79.9% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,454 - 1,476

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #74 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_mathematical. Source rank: #80. Votes: 1041. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,434 - 1,470

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #117 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_medicine_and_healthcare. Source rank: #131. Votes: 1190. Organization: alibaba. License: Apache 2.0.

66.5% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,422 - 1,457

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 #71 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_software_and_it_services. Source rank: #76. Votes: 7342. Organization: alibaba. License: Apache 2.0.

81.4% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,482 - 1,497

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 #119 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_writing_and_literature_and_language. Source rank: #133. Votes: 4821. Organization: alibaba. License: Apache 2.0.

68.5% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,388 - 1,407

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #45 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: expert. Source rank: #48. Votes: 2018. Organization: alibaba. License: Apache 2.0.

86.5% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,468 - 1,494

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 #59 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 84.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_business_and_management_and_financial_operations. Source rank: #62. Votes: 3457. Organization: alibaba. License: Apache 2.0.

84.3% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,426 - 1,446

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 #101 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_entertainment_and_sports_and_media. Source rank: #110. Votes: 4557. Organization: alibaba. License: Apache 2.0.

73.3% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,384 - 1,403

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

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

Rank #64 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_legal_and_government. Source rank: #67. Votes: 1417. Organization: alibaba. License: Apache 2.0.

81.9% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,433 - 1,465

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 #45 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 88.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_life_and_physical_and_social_science. Source rank: #47. Votes: 2904. Organization: alibaba. License: Apache 2.0.

88.2% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,455 - 1,478

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #60 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_mathematical. Source rank: #63. Votes: 1041. Organization: alibaba. License: Apache 2.0.

83.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,438 - 1,474

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 #93 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 73.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_medicine_and_healthcare. Source rank: #101. Votes: 1190. Organization: alibaba. License: Apache 2.0.

73.4% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,420 - 1,455

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 #46 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_software_and_it_services. Source rank: #48. Votes: 7342. Organization: alibaba. License: Apache 2.0.

88% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,472 - 1,487

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 #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_writing_and_literature_and_language. Source rank: #103. Votes: 4821. Organization: alibaba. License: Apache 2.0.

74.9% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,397 - 1,416

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #34 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36.1%
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

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

51.5% percentile inside its fair comparison set

36.1%Raw benchmark valueCI 29.5% - 42.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #10 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 11.3%
Percentile: 88.4%
Last updated: recent
Eligibility: headline eligible

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

88.4% percentile inside its fair comparison set

11.3%Raw benchmark valueCI 6.5% - 16%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #70 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.4%
Percentile: 48.9%
Last updated: recent
Eligibility: headline eligible

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

48.9% percentile inside its fair comparison set

82.4%Raw benchmark valueCI 81.5% - 83.4%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #40 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.6%
Percentile: 43.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Alibaba.

43.5% percentile inside its fair comparison set

48.6%Raw benchmark valueCI 44.4% - 52.7%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #91 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 28.7%
Percentile: 5.3%
Last updated: recent
Eligibility: headline eligible

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

5.3% percentile inside its fair comparison set

28.7%Raw benchmark valueCI 24.8% - 32.6%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #38 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.8%
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

83.8%Raw benchmark valueCI 80% - 87.7%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #7 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 52.4%
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

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

92.6% percentile inside its fair comparison set

52.4%Raw benchmark valueCI 45.6% - 59.2%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #30 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 38.1%
Percentile: 12.1%
Last updated: recent
Eligibility: headline eligible

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

12.1% percentile inside its fair comparison set

38.1%Raw benchmark valueCI 29.5% - 46.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #82 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.9%
Percentile: 37.2%
Last updated: recent
Eligibility: headline eligible

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

37.2% percentile inside its fair comparison set

70.9%Raw benchmark valueCI 69.1% - 72.6%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #31 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.6%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

53.8% percentile inside its fair comparison set

76.6%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #38 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.3%
Percentile: 43.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

43.1% percentile inside its fair comparison set

75.3%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #31 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.9%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

53.8% percentile inside its fair comparison set

84.9%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #29 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.8%
Percentile: 56.9%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

56.9% percentile inside its fair comparison set

48.8%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #57 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Long context1 benchmark93.4%

Long Context Reasoning

AA · Long context · Objective

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

Rank #32 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 82%
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

93.4% percentile inside its fair comparison set

82%Raw benchmark value

Vision understanding16 benchmarks67.2%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #62 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.3%
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

70.7% percentile inside its fair comparison set

76.3%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,243
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #58. Votes: 6422. Organization: alibaba. License: Apache 2.0.

63.3% percentile inside its fair comparison set

1,243Raw benchmark valueCI 1,234 - 1,251

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #67 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,191
Percentile: 19.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing_vision. Source rank: #76. Votes: 597. Organization: alibaba. License: Apache 2.0.

19.5% percentile inside its fair comparison set

1,191Raw benchmark valueCI 1,165 - 1,216

Vision Arena · Diagram

AR · Vision understanding · Human

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

Rank #49 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,273
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: diagram. Source rank: #54. Votes: 1579. Organization: alibaba. License: Apache 2.0.

51.5% percentile inside its fair comparison set

1,273Raw benchmark valueCI 1,257 - 1,288

Vision Arena · English

AR · Vision understanding · Human

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

Rank #58 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,235
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #64. Votes: 2102. Organization: alibaba. License: Apache 2.0.

58.7% percentile inside its fair comparison set

1,235Raw benchmark valueCI 1,221 - 1,249

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #35 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 64.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: homework. Source rank: #39. Votes: 730. Organization: alibaba. License: Apache 2.0.

64.6% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,270 - 1,314

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,196
Percentile: 27.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: humor. Source rank: #63. Votes: 283. Organization: alibaba. License: Apache 2.0.

27.4% percentile inside its fair comparison set

1,196Raw benchmark valueCI 1,160 - 1,232

Vision Arena · Ocr

AR · Vision understanding · Human

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

Rank #48 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 53%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: ocr. Source rank: #52. Votes: 4297. Organization: alibaba. License: Apache 2.0.

53% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,252 - 1,272

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,270
Percentile: 73.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #41. Votes: 6422. Organization: alibaba. License: Apache 2.0.

73.4% percentile inside its fair comparison set

1,270Raw benchmark valueCI 1,261 - 1,279

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 35.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing_vision. Source rank: #61. Votes: 597. Organization: alibaba. License: Apache 2.0.

35.4% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,207 - 1,256

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: diagram. Source rank: #41. Votes: 1579. Organization: alibaba. License: Apache 2.0.

62.6% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,271 - 1,302

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #47 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,266
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #50. Votes: 2102. Organization: alibaba. License: Apache 2.0.

66.7% percentile inside its fair comparison set

1,266Raw benchmark valueCI 1,252 - 1,279

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

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

Rank #31 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,302
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: homework. Source rank: #34. Votes: 730. Organization: alibaba. License: Apache 2.0.

68.8% percentile inside its fair comparison set

1,302Raw benchmark valueCI 1,280 - 1,324

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #48 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 35.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: humor. Source rank: #55. Votes: 283. Organization: alibaba. License: Apache 2.0.

35.6% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,190 - 1,261

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #37 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: ocr. Source rank: #40. Votes: 4297. Organization: alibaba. License: Apache 2.0.

64% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,271 - 1,291

MMMU Pro

VALS-AI · Vision understanding · Objective

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

Rank #28 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.9%
Percentile: 67.5%
Last updated: recent
Eligibility: headline eligible

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

67.5% percentile inside its fair comparison set

83.9%Raw benchmark valueCI 82.2% - 85.7%

Document understanding1 benchmark51.2%

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #43 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.9%
Percentile: 51.2%
Last updated: recent
Eligibility: headline eligible

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

51.2% percentile inside its fair comparison set

64.9%Raw benchmark valueCI 63.1% - 66.8%

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #55 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 84.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #58. Votes: 1336. Organization: alibaba. License: Apache 2.0.

84.7% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,483 - 1,516

Text Arena · French

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: french. Source rank: #76. Votes: 581. Organization: alibaba. License: Apache 2.0.

73.9% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,443 - 1,493

Text Arena · German

AR · Multilingual · Human

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

Rank #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: german. Source rank: #89. Votes: 280. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,401 - 1,471

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: japanese. Source rank: #81. Votes: 328. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,370 - 1,440

Text Arena · Korean

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: korean. Source rank: #76. Votes: 304. Organization: alibaba. License: Apache 2.0.

72.5% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,364 - 1,434

Text Arena · Non English

AR · Multilingual · Human

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

Rank #83 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 78.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: non_english. Source rank: #91. Votes: 11436. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,423 - 1,436

Text Arena · Polish

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: polish. Source rank: #78. Votes: 263. Organization: alibaba. License: Apache 2.0.

67.8% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,408 - 1,479

Text Arena · Russian

AR · Multilingual · Human

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

Rank #103 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 70.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: russian. Source rank: #118. Votes: 2328. Organization: alibaba. License: Apache 2.0.

70.1% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,408 - 1,433

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: spanish. Source rank: #90. Votes: 569. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,408 - 1,458

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #46 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 87.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #49. Votes: 1336. Organization: alibaba. License: Apache 2.0.

87.2% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,488 - 1,521

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #44 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: french. Source rank: #47. Votes: 581. Organization: alibaba. License: Apache 2.0.

83.3% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,442 - 1,493

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 76.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: german. Source rank: #74. Votes: 280. Organization: alibaba. License: Apache 2.0.

76.5% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,402 - 1,471

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: japanese. Source rank: #78. Votes: 328. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,362 - 1,430

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #58 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 76.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: korean. Source rank: #64. Votes: 304. Organization: alibaba. License: Apache 2.0.

76.6% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,366 - 1,434

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: non_english. Source rank: #71. Votes: 11436. Organization: alibaba. License: Apache 2.0.

83% percentile inside its fair comparison set

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

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #44 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: polish. Source rank: #50. Votes: 263. Organization: alibaba. License: Apache 2.0.

78.4% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,412 - 1,483

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: russian. Source rank: #103. Votes: 2328. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,404 - 1,429

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: spanish. Source rank: #57. Votes: 569. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,425 - 1,475

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #44 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #49. Votes: 337. Organization: alibaba. License: Apache 2.0.

58.7% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,254 - 1,320

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,322
Percentile: 67.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #38. Votes: 337. Organization: alibaba. License: Apache 2.0.

67.3% percentile inside its fair comparison set

1,322Raw benchmark valueCI 1,289 - 1,354

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

Model profile · Qwen

qwen3.8-27b

Open weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

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

Visible coverage: 47.3%
Verified coverage: 47.3%
Spread: 96.9%
Last verified: Oct 3, 2026

66%capability fit

textcodevisiondocument3 aliases43 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

Chat / text35 benchmarks68.5%

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 #76 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 34
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

86.5% percentile inside its fair comparison set

34Raw 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 #314 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.6%
Percentile: 30.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

30.9% percentile inside its fair comparison set

15.6%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 #33 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.7%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

92.9% percentile inside its fair comparison set

69.7%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 #186 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.5 /1M input tokens
Percentile: 49.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

49.7% percentile inside its fair comparison set

$0.5 /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 #207 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3 /1M output tokens
Percentile: 44.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

44.1% percentile inside its fair comparison set

$3 /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 #230 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.1 tokens/s
Percentile: 12.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

12.6% percentile inside its fair comparison set

46.1 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 #166 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.92s
Percentile: 37.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

37.5% percentile inside its fair comparison set

3.92sRaw 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 #214 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.29s
Percentile: 18.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

18.7% percentile inside its fair comparison set

47.29sRaw 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 #90 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #99. Votes: 18462. Organization: alibaba. License: Apache 2.0.

76.3% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,432 - 1,443

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 #144 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing. Source rank: #163. Votes: 3654. Organization: alibaba. License: Apache 2.0.

61.8% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,353 - 1,374

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 #103 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #113. Votes: 7018. Organization: alibaba. License: Apache 2.0.

72.9% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,432 - 1,447

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 76.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: exclude_ties. Source rank: #101. Votes: 13519. Organization: alibaba. License: Apache 2.0.

76.1% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,426 - 1,440

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 #81 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 78.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts. Source rank: #89. Votes: 12126. Organization: alibaba. License: Apache 2.0.

78.7% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,457 - 1,470

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 #103 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 72.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts_english. Source rank: #114. Votes: 4669. Organization: alibaba. License: Apache 2.0.

72.7% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,448 - 1,466

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 76.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: instruction_following. Source rank: #101. Votes: 6537. Organization: alibaba. License: Apache 2.0.

76.1% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,418 - 1,434

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 74.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: longer_query. Source rank: #100. Votes: 8253. Organization: alibaba. License: Apache 2.0.

74.6% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,437 - 1,452

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 #91 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 75.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: multi_turn. Source rank: #103. Votes: 2983. Organization: alibaba. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,431 - 1,453

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 #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #74. Votes: 18462. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,435 - 1,446

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 #118 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing. Source rank: #128. Votes: 3654. Organization: alibaba. License: Apache 2.0.

68.7% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,370 - 1,391

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 #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 80.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #81. Votes: 7018. Organization: alibaba. License: Apache 2.0.

80.1% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,439 - 1,454

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 #70 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 81.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: exclude_ties. Source rank: #76. Votes: 13519. Organization: alibaba. License: Apache 2.0.

81.6% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,428 - 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 #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts. Source rank: #57. Votes: 12126. Organization: alibaba. License: Apache 2.0.

85.9% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,455 - 1,467

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 #63 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: hard_prompts_english. Source rank: #66. Votes: 4669. Organization: alibaba. License: Apache 2.0.

83.4% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,451 - 1,469

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 #58 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: instruction_following. Source rank: #61. Votes: 6537. Organization: alibaba. License: Apache 2.0.

84.8% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,430 - 1,446

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 #61 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: longer_query. Source rank: #64. Votes: 8253. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,441 - 1,456

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 #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 79.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: multi_turn. Source rank: #83. Votes: 2983. Organization: alibaba. License: Apache 2.0.

79.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,431 - 1,453

Instruction following

LB · Chat / text · Objective

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

Rank #18 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.7%
Percentile: 73.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

73.8% percentile inside its fair comparison set

72.7%Raw benchmark value

Language

LB · Chat / text · Objective

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.3%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

21.5% percentile inside its fair comparison set

74.3%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #12 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.9%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

83.1% percentile inside its fair comparison set

74.9%Raw benchmark value

Simplify

LB · Chat / text · Objective

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

Rank #25 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.7%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

63.1% percentile inside its fair comparison set

66.7%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #27 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.1%
Percentile: 60%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

60% percentile inside its fair comparison set

73.1%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #17 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.9%
Percentile: 75.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

75.4% percentile inside its fair comparison set

75.9%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #59 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.5%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

12.3% percentile inside its fair comparison set

90.5%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

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

Rank #46 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 56.5%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

30.8% percentile inside its fair comparison set

56.5%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76%
Percentile: 24.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

24.6% percentile inside its fair comparison set

76%Raw benchmark value

Coding21 benchmarks58.5%

SciCode

AA · Coding · Objective

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

Rank #105 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.6%
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

47.5% percentile inside its fair comparison set

46.6%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 #67 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: coding. Source rank: #73. Votes: 5208. Organization: alibaba. License: Apache 2.0.

82.2% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,493 - 1,511

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 #43 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 88.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: coding. Source rank: #44. Votes: 5208. Organization: alibaba. License: Apache 2.0.

88.7% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,477 - 1,494

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 #36 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.9%
Percentile: 62.4%
Last updated: recent
Eligibility: headline eligible

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

62.4% percentile inside its fair comparison set

64.9%Raw benchmark valueCI 55.4% - 74.3%

WebDev Arena

AR · Coding · Human

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

Rank #27 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,591
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #28. Votes: 12388. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,591Raw benchmark valueCI 1,584 - 1,598

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #27 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,576
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: webdev-html. Source rank: #28. Votes: 1877. Organization: alibaba. License: Apache 2.0.

79.2% percentile inside its fair comparison set

1,576Raw benchmark valueCI 1,561 - 1,591

Code Arena · Webdev React

AR · Coding · Human

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

Rank #26 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,599
Percentile: 77.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: webdev-react. Source rank: #27. Votes: 8107. Organization: alibaba. License: Apache 2.0.

77.9% percentile inside its fair comparison set

1,599Raw benchmark valueCI 1,591 - 1,607

Code Migration

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 #51 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 14.2%
Percentile: 26.5%
Last updated: recent
Eligibility: headline eligible

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

26.5% percentile inside its fair comparison set

14.2%Raw benchmark valueCI 5.9% - 22.4%

IOI

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 #31 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 39.1%
Percentile: 18.9%
Last updated: recent
Eligibility: headline eligible

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

18.9% percentile inside its fair comparison set

39.1%Raw benchmark valueCI 29.4% - 48.7%

ProgramBench

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 #46 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

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

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Terminal-Bench 2.1

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 #39 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58.4%
Percentile: 43.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

43.3% percentile inside its fair comparison set

58.4%Raw benchmark valueCI 48.1% - 68.7%

Code Arena · Image To Webdev

AR · Coding · Human

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

Rank #10 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,582
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: image_to_webdev. Source rank: #11. Votes: 2439. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,582Raw benchmark valueCI 1,570 - 1,595

SWE-bench Verified

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 #15 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86%
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

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

82.9% percentile inside its fair comparison set

86%Raw benchmark valueCI 83% - 89%

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 #41 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84%
Percentile: 68%
Last updated: recent
Eligibility: headline eligible

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

68% percentile inside its fair comparison set

84%Raw benchmark valueCI 82% - 86%

Agentic coding

LB · Coding · Objective

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

Rank #13 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.4%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

81.5% percentile inside its fair comparison set

61.4%Raw benchmark value

Coding

LB · Coding · Objective

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

Rank #47 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.7%
Percentile: 29.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

29.2% percentile inside its fair comparison set

75.7%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #57 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 59.1%
Percentile: 27.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

27.7% percentile inside its fair comparison set

59.1%Raw benchmark value

TypeScript

LB · Coding · Objective

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

Rank #16 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

81.5% percentile inside its fair comparison set

50%Raw benchmark value

Python

LB · Coding · Objective

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

Rank #3 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

98.5% percentile inside its fair comparison set

75%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #34 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77.5%
Percentile: 52.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

52.3% percentile inside its fair comparison set

77.5%Raw benchmark value

Coding completion

LB · Coding · Objective

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.9%
Percentile: 24.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

24.6% percentile inside its fair comparison set

73.9%Raw benchmark value

Reasoning / math / science18 benchmarks54.8%

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 #90 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.9%
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

83.2% percentile inside its fair comparison set

33.9%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 #42 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 90.5%
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

91.9% percentile inside its fair comparison set

90.5%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 #102 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.4%
Percentile: 78.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

78.3% percentile inside its fair comparison set

5.4%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 #63 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: math. Source rank: #66. Votes: 897. Organization: alibaba. License: Apache 2.0.

82.7% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,437 - 1,476

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 #51 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: math. Source rank: #53. Votes: 897. Organization: alibaba. License: Apache 2.0.

86.1% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,440 - 1,479

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #39 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 16%
Percentile: 14.3%
Last updated: recent
Eligibility: headline eligible

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

14.3% percentile inside its fair comparison set

16%Raw benchmark valueCI 8.8% - 23.2%

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 #33 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.9%
Percentile: 75%
Last updated: recent
Eligibility: headline eligible

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

75% percentile inside its fair comparison set

88.9%Raw benchmark valueCI 85.8% - 92%

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 #64 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.3%
Percentile: 49.6%
Last updated: recent
Eligibility: headline eligible

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

49.6% percentile inside its fair comparison set

84.3%Raw benchmark valueCI 83.6% - 85%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #50 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.2%
Percentile: 24.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

24.6% percentile inside its fair comparison set

86.2%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #51 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

23.1% percentile inside its fair comparison set

80%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

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

Rank #33 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

83.1% percentile inside its fair comparison set

98%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #50 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

26.2% percentile inside its fair comparison set

65%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

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

Rank #57 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.1%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

26.2% percentile inside its fair comparison set

94.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #51 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.7%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

23.1% percentile inside its fair comparison set

87.7%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 59.6%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

1.5% percentile inside its fair comparison set

59.6%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #30 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.5%
Percentile: 55.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

55.4% percentile inside its fair comparison set

96.5%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #48 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

41.5% percentile inside its fair comparison set

96%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

Rank #50 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

30.8% percentile inside its fair comparison set

68%Raw benchmark value

Professional reasoning32 benchmarks47.3%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #75 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: expert. Source rank: #80. Votes: 2018. Organization: alibaba. License: Apache 2.0.

77.4% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,462 - 1,489

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 #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 74.5%
Last updated: recent
Eligibility: headline eligible

74.5% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,426 - 1,447

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 #124 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 67.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_entertainment_and_sports_and_media. Source rank: #139. Votes: 4557. Organization: alibaba. License: Apache 2.0.

67.1% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,373 - 1,392

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 73.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_legal_and_government. Source rank: #108. Votes: 1417. Organization: alibaba. License: Apache 2.0.

73.1% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,423 - 1,456

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 #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 79.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_life_and_physical_and_social_science. Source rank: #83. Votes: 2904. Organization: alibaba. License: Apache 2.0.

79.9% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,454 - 1,476

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #74 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_mathematical. Source rank: #80. Votes: 1041. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,434 - 1,470

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #117 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_medicine_and_healthcare. Source rank: #131. Votes: 1190. Organization: alibaba. License: Apache 2.0.

66.5% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,422 - 1,457

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 #71 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_software_and_it_services. Source rank: #76. Votes: 7342. Organization: alibaba. License: Apache 2.0.

81.4% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,482 - 1,497

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 #119 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_writing_and_literature_and_language. Source rank: #133. Votes: 4821. Organization: alibaba. License: Apache 2.0.

68.5% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,388 - 1,407

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #45 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: expert. Source rank: #48. Votes: 2018. Organization: alibaba. License: Apache 2.0.

86.5% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,468 - 1,494

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 #59 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 84.3%
Last updated: recent
Eligibility: headline eligible

84.3% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,426 - 1,446

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 #101 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_entertainment_and_sports_and_media. Source rank: #110. Votes: 4557. Organization: alibaba. License: Apache 2.0.

73.3% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,384 - 1,403

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

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

Rank #64 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_legal_and_government. Source rank: #67. Votes: 1417. Organization: alibaba. License: Apache 2.0.

81.9% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,433 - 1,465

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 #45 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 88.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_life_and_physical_and_social_science. Source rank: #47. Votes: 2904. Organization: alibaba. License: Apache 2.0.

88.2% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,455 - 1,478

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #60 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_mathematical. Source rank: #63. Votes: 1041. Organization: alibaba. License: Apache 2.0.

83.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,438 - 1,474

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 #93 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 73.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_medicine_and_healthcare. Source rank: #101. Votes: 1190. Organization: alibaba. License: Apache 2.0.

73.4% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,420 - 1,455

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 #46 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_software_and_it_services. Source rank: #48. Votes: 7342. Organization: alibaba. License: Apache 2.0.

88% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,472 - 1,487

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 #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: industry_writing_and_literature_and_language. Source rank: #103. Votes: 4821. Organization: alibaba. License: Apache 2.0.

74.9% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,397 - 1,416

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #34 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36.1%
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

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

51.5% percentile inside its fair comparison set

36.1%Raw benchmark valueCI 29.5% - 42.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #10 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 11.3%
Percentile: 88.4%
Last updated: recent
Eligibility: headline eligible

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

88.4% percentile inside its fair comparison set

11.3%Raw benchmark valueCI 6.5% - 16%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #70 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.4%
Percentile: 48.9%
Last updated: recent
Eligibility: headline eligible

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

48.9% percentile inside its fair comparison set

82.4%Raw benchmark valueCI 81.5% - 83.4%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #40 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.6%
Percentile: 43.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Alibaba.

43.5% percentile inside its fair comparison set

48.6%Raw benchmark valueCI 44.4% - 52.7%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #91 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 28.7%
Percentile: 5.3%
Last updated: recent
Eligibility: headline eligible

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

5.3% percentile inside its fair comparison set

28.7%Raw benchmark valueCI 24.8% - 32.6%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #38 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.8%
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

83.8%Raw benchmark valueCI 80% - 87.7%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #7 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 52.4%
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

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

92.6% percentile inside its fair comparison set

52.4%Raw benchmark valueCI 45.6% - 59.2%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #30 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 38.1%
Percentile: 12.1%
Last updated: recent
Eligibility: headline eligible

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

12.1% percentile inside its fair comparison set

38.1%Raw benchmark valueCI 29.5% - 46.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #82 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.9%
Percentile: 37.2%
Last updated: recent
Eligibility: headline eligible

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

37.2% percentile inside its fair comparison set

70.9%Raw benchmark valueCI 69.1% - 72.6%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #31 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.6%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

53.8% percentile inside its fair comparison set

76.6%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #38 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.3%
Percentile: 43.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

43.1% percentile inside its fair comparison set

75.3%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #31 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.9%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

53.8% percentile inside its fair comparison set

84.9%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #29 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.8%
Percentile: 56.9%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

56.9% percentile inside its fair comparison set

48.8%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #57 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Long context1 benchmark93.4%

Long Context Reasoning

AA · Long context · Objective

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

Rank #32 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 82%
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

93.4% percentile inside its fair comparison set

82%Raw benchmark value

Vision understanding16 benchmarks67.2%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #62 · Source label: Qwen3.8 27B (Xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.3%
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

70.7% percentile inside its fair comparison set

76.3%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #52 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,243
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #58. Votes: 6422. Organization: alibaba. License: Apache 2.0.

63.3% percentile inside its fair comparison set

1,243Raw benchmark valueCI 1,234 - 1,251

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #67 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,191
Percentile: 19.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing_vision. Source rank: #76. Votes: 597. Organization: alibaba. License: Apache 2.0.

19.5% percentile inside its fair comparison set

1,191Raw benchmark valueCI 1,165 - 1,216

Vision Arena · Diagram

AR · Vision understanding · Human

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

Rank #49 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,273
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: diagram. Source rank: #54. Votes: 1579. Organization: alibaba. License: Apache 2.0.

51.5% percentile inside its fair comparison set

1,273Raw benchmark valueCI 1,257 - 1,288

Vision Arena · English

AR · Vision understanding · Human

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

Rank #58 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,235
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #64. Votes: 2102. Organization: alibaba. License: Apache 2.0.

58.7% percentile inside its fair comparison set

1,235Raw benchmark valueCI 1,221 - 1,249

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #35 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 64.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: homework. Source rank: #39. Votes: 730. Organization: alibaba. License: Apache 2.0.

64.6% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,270 - 1,314

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,196
Percentile: 27.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: humor. Source rank: #63. Votes: 283. Organization: alibaba. License: Apache 2.0.

27.4% percentile inside its fair comparison set

1,196Raw benchmark valueCI 1,160 - 1,232

Vision Arena · Ocr

AR · Vision understanding · Human

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

Rank #48 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 53%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: ocr. Source rank: #52. Votes: 4297. Organization: alibaba. License: Apache 2.0.

53% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,252 - 1,272

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,270
Percentile: 73.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: overall. Source rank: #41. Votes: 6422. Organization: alibaba. License: Apache 2.0.

73.4% percentile inside its fair comparison set

1,270Raw benchmark valueCI 1,261 - 1,279

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 35.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: creative_writing_vision. Source rank: #61. Votes: 597. Organization: alibaba. License: Apache 2.0.

35.4% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,207 - 1,256

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: diagram. Source rank: #41. Votes: 1579. Organization: alibaba. License: Apache 2.0.

62.6% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,271 - 1,302

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #47 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,266
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: english. Source rank: #50. Votes: 2102. Organization: alibaba. License: Apache 2.0.

66.7% percentile inside its fair comparison set

1,266Raw benchmark valueCI 1,252 - 1,279

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

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

Rank #31 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,302
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: homework. Source rank: #34. Votes: 730. Organization: alibaba. License: Apache 2.0.

68.8% percentile inside its fair comparison set

1,302Raw benchmark valueCI 1,280 - 1,324

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #48 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 35.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: humor. Source rank: #55. Votes: 283. Organization: alibaba. License: Apache 2.0.

35.6% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,190 - 1,261

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #37 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: ocr. Source rank: #40. Votes: 4297. Organization: alibaba. License: Apache 2.0.

64% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,271 - 1,291

MMMU Pro

VALS-AI · Vision understanding · Objective

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

Rank #28 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.9%
Percentile: 67.5%
Last updated: recent
Eligibility: headline eligible

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

67.5% percentile inside its fair comparison set

83.9%Raw benchmark valueCI 82.2% - 85.7%

Document understanding1 benchmark51.2%

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #43 · Source label: alibaba/qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.9%
Percentile: 51.2%
Last updated: recent
Eligibility: headline eligible

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

51.2% percentile inside its fair comparison set

64.9%Raw benchmark valueCI 63.1% - 66.8%

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #55 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 84.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #58. Votes: 1336. Organization: alibaba. License: Apache 2.0.

84.7% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,483 - 1,516

Text Arena · French

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: french. Source rank: #76. Votes: 581. Organization: alibaba. License: Apache 2.0.

73.9% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,443 - 1,493

Text Arena · German

AR · Multilingual · Human

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

Rank #76 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: german. Source rank: #89. Votes: 280. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,401 - 1,471

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: japanese. Source rank: #81. Votes: 328. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,370 - 1,440

Text Arena · Korean

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: korean. Source rank: #76. Votes: 304. Organization: alibaba. License: Apache 2.0.

72.5% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,364 - 1,434

Text Arena · Non English

AR · Multilingual · Human

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

Rank #83 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 78.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: non_english. Source rank: #91. Votes: 11436. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,423 - 1,436

Text Arena · Polish

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: polish. Source rank: #78. Votes: 263. Organization: alibaba. License: Apache 2.0.

67.8% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,408 - 1,479

Text Arena · Russian

AR · Multilingual · Human

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

Rank #103 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 70.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: russian. Source rank: #118. Votes: 2328. Organization: alibaba. License: Apache 2.0.

70.1% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,408 - 1,433

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #81 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: spanish. Source rank: #90. Votes: 569. Organization: alibaba. License: Apache 2.0.

69.1% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,408 - 1,458

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #46 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 87.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #49. Votes: 1336. Organization: alibaba. License: Apache 2.0.

87.2% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,488 - 1,521

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #44 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: french. Source rank: #47. Votes: 581. Organization: alibaba. License: Apache 2.0.

83.3% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,442 - 1,493

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 76.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: german. Source rank: #74. Votes: 280. Organization: alibaba. License: Apache 2.0.

76.5% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,402 - 1,471

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #68 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: japanese. Source rank: #78. Votes: 328. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,362 - 1,430

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #58 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 76.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: korean. Source rank: #64. Votes: 304. Organization: alibaba. License: Apache 2.0.

76.6% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,366 - 1,434

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: non_english. Source rank: #71. Votes: 11436. Organization: alibaba. License: Apache 2.0.

83% percentile inside its fair comparison set

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

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #44 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: polish. Source rank: #50. Votes: 263. Organization: alibaba. License: Apache 2.0.

78.4% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,412 - 1,483

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #95 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: russian. Source rank: #103. Votes: 2328. Organization: alibaba. License: Apache 2.0.

72.4% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,404 - 1,429

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #54 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: spanish. Source rank: #57. Votes: 569. Organization: alibaba. License: Apache 2.0.

79.5% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,425 - 1,475

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #44 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #49. Votes: 337. Organization: alibaba. License: Apache 2.0.

58.7% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,254 - 1,320

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: qwen3.8-27b

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,322
Percentile: 67.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3.8-27b`. Category: chinese. Source rank: #38. Votes: 337. Organization: alibaba. License: Apache 2.0.

67.3% percentile inside its fair comparison set

1,322Raw benchmark valueCI 1,289 - 1,354

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

qwen3.8-27b

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

qwen3.8-27b

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks