Model profile · Qwen

qwen3-235b-a22b-instruct-2507

Open weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 34.2%
Verified coverage: 34.2%
Spread: n/a
Last verified: Jun 20, 2026

textcodedocument2 aliases29 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text38 benchmarks61.1%

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 #136 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18
Percentile: 65.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

65.8% percentile inside its fair comparison set

18Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

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

Rank #160 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.8%
Percentile: 46.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

46.6% percentile inside its fair comparison set

16.8%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 #71 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29.2%
Percentile: 76.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

76.5% percentile inside its fair comparison set

29.2%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #112 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.1%
Percentile: 64.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

64.8% percentile inside its fair comparison set

46.1%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

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

Rank #102 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.4 /1M tokens
Percentile: 63.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

63.4% percentile inside its fair comparison set

$0.4 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #105 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.2 /1M input tokens
Percentile: 66.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

66.3% percentile inside its fair comparison set

$0.2 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #107 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.8 /1M output tokens
Percentile: 61.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

61.6% percentile inside its fair comparison set

$0.8 /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 #141 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 63.2 tokens/s
Percentile: 33.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33.3% percentile inside its fair comparison set

63.2 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #112 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.39s
Percentile: 47.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

47.1% percentile inside its fair comparison set

2.39sRaw 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 #66 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.39s
Percentile: 69%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

69% percentile inside its fair comparison set

2.39sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #76 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44
Percentile: 71%
Last updated: recent
Eligibility: benchmark_derived_model

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

71% percentile inside its fair comparison set

44Raw 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 #66

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 80%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: overall. Source rank: #84. Votes: 97241. Organization: alibaba. License: Apache 2.0.

80% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,421 - 1,426

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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 74.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: creative_writing. Source rank: #105. Votes: 13593. Organization: alibaba. License: Apache 2.0.

74.3% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,375 - 1,386

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 #74

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 77.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: english. Source rank: #92. Votes: 45078. Organization: alibaba. License: Apache 2.0.

77.5% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,427 - 1,434

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 #65

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: exclude_ties. Source rank: #83. Votes: 69277. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,411 - 1,419

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 #58

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 82.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts. Source rank: #74. Votes: 52312. Organization: alibaba. License: Apache 2.0.

82.5% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,445 - 1,451

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 #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 79.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts_english. Source rank: #84. Votes: 25618. Organization: alibaba. License: Apache 2.0.

79.6% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,447 - 1,455

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 #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 80.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: instruction_following. Source rank: #80. Votes: 26979. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,412 - 1,421

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 #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 79.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: longer_query. Source rank: #80. Votes: 25800. Organization: alibaba. License: Apache 2.0.

79.3% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,431 - 1,440

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 #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 83.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: multi_turn. Source rank: #71. Votes: 17023. Organization: alibaba. License: Apache 2.0.

83.6% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,433 - 1,443

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 #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 79.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: overall. Source rank: #80. Votes: 97241. Organization: alibaba. License: Apache 2.0.

79.7% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,417 - 1,422

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 #79

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 75.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: creative_writing. Source rank: #96. Votes: 13593. Organization: alibaba. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,371 - 1,382

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 #75

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 77.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: english. Source rank: #88. Votes: 45078. Organization: alibaba. License: Apache 2.0.

77.2% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,422 - 1,428

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 #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 79.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: exclude_ties. Source rank: #80. Votes: 69277. Organization: alibaba. License: Apache 2.0.

79.7% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,404 - 1,411

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 #52

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 84.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts. Source rank: #66. Votes: 52312. Organization: alibaba. License: Apache 2.0.

84.3% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,430 - 1,437

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 #61

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 81.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts_english. Source rank: #72. Votes: 25618. Organization: alibaba. License: Apache 2.0.

81.5% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,432 - 1,441

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 #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 83.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: instruction_following. Source rank: #68. Votes: 26979. Organization: alibaba. License: Apache 2.0.

83.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,405 - 1,413

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 #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 84.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: longer_query. Source rank: #60. Votes: 25800. Organization: alibaba. License: Apache 2.0.

84.5% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,423 - 1,432

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 #51

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 84.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: multi_turn. Source rank: #63. Votes: 17023. Organization: alibaba. License: Apache 2.0.

84.5% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,428 - 1,438

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 #97

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 21.7%
Percentile: 11.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

11.1% percentile inside its fair comparison set

21.7%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 #74

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.1%
Percentile: 32.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

32.4% percentile inside its fair comparison set

66.1%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 #93

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18%
Percentile: 14.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

14.8% percentile inside its fair comparison set

18%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 #95

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 21.9%
Percentile: 13%
Last updated: archived
Eligibility: benchmark_derived_model

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

13% percentile inside its fair comparison set

21.9%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 #98

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 19.4%
Percentile: 10.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

10.2% percentile inside its fair comparison set

19.4%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 #91

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 27.7%
Percentile: 16.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

16.7% percentile inside its fair comparison set

27.7%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 #50

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91%
Percentile: 57.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

57.4% percentile inside its fair comparison set

91%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 #86

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 39.2%
Percentile: 21.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

21.3% percentile inside its fair comparison set

39.2%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 #78

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 29.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

29.9% percentile inside its fair comparison set

68%Raw benchmark value

Coding11 benchmarks41%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #126 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.2%
Percentile: 59.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

59.3% percentile inside its fair comparison set

15.2%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #118 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36%
Percentile: 68.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

68.8% percentile inside its fair comparison set

36%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 #62

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: coding. Source rank: #78. Votes: 21307. Organization: alibaba. License: Apache 2.0.

80.9% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,469 - 1,478

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 #55

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 83.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: coding. Source rank: #66. Votes: 21307. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,441 - 1,450

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 #96

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 13.3%
Percentile: 12%
Last updated: archived
Eligibility: benchmark_derived_model

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

12% percentile inside its fair comparison set

13.3%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 #75

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.6%
Percentile: 31.5%
Last updated: archived
Eligibility: benchmark_derived_model

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

31.5% percentile inside its fair comparison set

69.6%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 #97

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 13.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

13.9% percentile inside its fair comparison set

10%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 #94

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 16.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

16.8% percentile inside its fair comparison set

10%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 #96

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20%
Percentile: 13.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

13.9% percentile inside its fair comparison set

20%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 #75

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.8%
Percentile: 35.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

35.2% percentile inside its fair comparison set

71.8%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 #77

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.4%
Percentile: 36.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

36.1% percentile inside its fair comparison set

67.4%Raw benchmark value

Reasoning / math / science15 benchmarks46.8%

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 #92 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.6%
Percentile: 75.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `hle`.

75.7% percentile inside its fair comparison set

10.6%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 #100 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.3%
Percentile: 73.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

73.5% percentile inside its fair comparison set

75.3%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 #284 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 79%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: math. Source rank: #85. Votes: 5924. Organization: alibaba. License: Apache 2.0.

79% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,412 - 1,428

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 #50

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 84.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: math. Source rank: #62. Votes: 5924. Organization: alibaba. License: Apache 2.0.

84.4% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,424 - 1,440

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #78

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 28.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

28.7% percentile inside its fair comparison set

68%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 #71

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.4%
Percentile: 35.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

35.2% percentile inside its fair comparison set

58.4%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 #92

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84%
Percentile: 16.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

16.7% percentile inside its fair comparison set

84%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 #80

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 21%
Percentile: 27.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

27.8% percentile inside its fair comparison set

21%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 #62

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.2%
Percentile: 46.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

46.3% percentile inside its fair comparison set

90.2%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 #80

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.9%
Percentile: 26.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

26.9% percentile inside its fair comparison set

76.9%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 #91

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.2%
Percentile: 17.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

17.6% percentile inside its fair comparison set

44.2%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 #61

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 43.5%
Percentile: 43.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

43.9% percentile inside its fair comparison set

43.5%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 #78

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84%
Percentile: 33.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

33.3% percentile inside its fair comparison set

84%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 #62

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62%
Percentile: 47.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

47.2% percentile inside its fair comparison set

62%Raw benchmark value

Professional reasoning23 benchmarks67.4%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #56

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 80%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: expert. Source rank: #73. Votes: 5893. Organization: alibaba. License: Apache 2.0.

80% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,444 - 1,460

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 #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 83.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_business_and_management_and_financial_operations. Source rank: #70. Votes: 17959. Organization: alibaba. License: Apache 2.0.

83.3% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,427 - 1,437

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 #85

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 74%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_entertainment_and_sports_and_media. Source rank: #105. Votes: 17725. Organization: alibaba. License: Apache 2.0.

74% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,373 - 1,382

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #65

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 78.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_legal_and_government. Source rank: #83. Votes: 6518. Organization: alibaba. License: Apache 2.0.

78.5% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,426 - 1,442

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 #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 80.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_life_and_physical_and_social_science. Source rank: #80. Votes: 15329. Organization: alibaba. License: Apache 2.0.

80.5% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,440 - 1,451

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 78.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_mathematical. Source rank: #82. Votes: 4926. Organization: alibaba. License: Apache 2.0.

78.6% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,424 - 1,442

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #53

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_medicine_and_healthcare. Source rank: #68. Votes: 5723. Organization: alibaba. License: Apache 2.0.

82.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,448 - 1,465

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 #61

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 81.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_software_and_it_services. Source rank: #77. Votes: 34735. Organization: alibaba. License: Apache 2.0.

81.5% percentile inside its fair comparison set

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

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 #77

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 76.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_writing_and_literature_and_language. Source rank: #95. Votes: 21690. Organization: alibaba. License: Apache 2.0.

76.5% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,393 - 1,402

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #45

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 84%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: expert. Source rank: #53. Votes: 5893. Organization: alibaba. License: Apache 2.0.

84% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,437 - 1,453

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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_business_and_management_and_financial_operations. Source rank: #69. Votes: 17959. Organization: alibaba. License: Apache 2.0.

82.4% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,413 - 1,423

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 #80

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 75.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_entertainment_and_sports_and_media. Source rank: #97. Votes: 17725. Organization: alibaba. License: Apache 2.0.

75.5% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,370 - 1,380

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 #63

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 79.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_legal_and_government. Source rank: #76. Votes: 6518. Organization: alibaba. License: Apache 2.0.

79.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,422 - 1,437

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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 82.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_life_and_physical_and_social_science. Source rank: #68. Votes: 15329. Organization: alibaba. License: Apache 2.0.

82.7% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,433 - 1,444

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #44

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 86%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_mathematical. Source rank: #52. Votes: 4926. Organization: alibaba. License: Apache 2.0.

86% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,432 - 1,450

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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 81%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_medicine_and_healthcare. Source rank: #65. Votes: 5723. Organization: alibaba. License: Apache 2.0.

81% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,437 - 1,454

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 #56

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 83.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_software_and_it_services. Source rank: #69. Votes: 34735. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,442 - 1,450

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 #74

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 77.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_writing_and_literature_and_language. Source rank: #89. Votes: 21690. Organization: alibaba. License: Apache 2.0.

77.5% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,386 - 1,395

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #92

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.7%
Percentile: 15.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

15.7% percentile inside its fair comparison set

44.7%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #87

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.8%
Percentile: 20.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

20.4% percentile inside its fair comparison set

48.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #85

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 3.7%
Percentile: 22.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

22.2% percentile inside its fair comparison set

3.7%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #93

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 34.4%
Percentile: 14.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

14.8% percentile inside its fair comparison set

34.4%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #88

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 30.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

30.6% percentile inside its fair comparison set

96.1%Raw benchmark value

Search / tool use1 benchmark47.2%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #164 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.3%
Percentile: 47.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

47.2% percentile inside its fair comparison set

33.3%Raw benchmark value

Long context1 benchmark52.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #150 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.2%
Percentile: 52.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

52.7% percentile inside its fair comparison set

31.2%Raw benchmark value

Multilingual14 benchmarks79.2%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #59

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: chinese. Source rank: #72. Votes: 4967. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,463 - 1,481

Text Arena · French

AR · Multilingual · Human

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

Rank #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 78.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: french. Source rank: #62. Votes: 1989. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,445 - 1,475

Text Arena · German

AR · Multilingual · Human

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

Rank #51

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 78.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: german. Source rank: #68. Votes: 1711. Organization: alibaba. License: Apache 2.0.

78.9% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,413 - 1,443

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 76.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: japanese. Source rank: #65. Votes: 1261. Organization: alibaba. License: Apache 2.0.

76.8% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,364 - 1,399

Text Arena · Korean

AR · Multilingual · Human

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

Rank #50

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 76.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: korean. Source rank: #64. Votes: 1731. Organization: alibaba. License: Apache 2.0.

76.4% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,368 - 1,399

Text Arena · Russian

AR · Multilingual · Human

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

Rank #60

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 79.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: russian. Source rank: #79. Votes: 8460. Organization: alibaba. License: Apache 2.0.

79.6% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,410 - 1,424

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #55

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 74.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: spanish. Source rank: #68. Votes: 2564. Organization: alibaba. License: Apache 2.0.

74.8% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,410 - 1,437

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #53

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: chinese. Source rank: #63. Votes: 4967. Organization: alibaba. License: Apache 2.0.

82.4% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,457 - 1,475

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #46

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 79.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: french. Source rank: #54. Votes: 1989. Organization: alibaba. License: Apache 2.0.

79.2% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,436 - 1,466

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #30

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 87.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: german. Source rank: #38. Votes: 1711. Organization: alibaba. License: Apache 2.0.

87.8% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,422 - 1,451

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #41

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: japanese. Source rank: #53. Votes: 1261. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,371 - 1,406

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #42

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: korean. Source rank: #51. Votes: 1731. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,377 - 1,408

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 78.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: russian. Source rank: #80. Votes: 8460. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,404 - 1,417

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 75.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: spanish. Source rank: #65. Votes: 2564. Organization: alibaba. License: Apache 2.0.

75.2% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,412 - 1,438

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

Model profile · Qwen

qwen3-235b-a22b-instruct-2507

Open weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 34.2%
Verified coverage: 34.2%
Spread: n/a
Last verified: Jun 20, 2026

textcodedocument2 aliases29 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text38 benchmarks61.1%

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 #136 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18
Percentile: 65.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

65.8% percentile inside its fair comparison set

18Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

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

Rank #160 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.8%
Percentile: 46.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

46.6% percentile inside its fair comparison set

16.8%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 #71 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29.2%
Percentile: 76.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

76.5% percentile inside its fair comparison set

29.2%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #112 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.1%
Percentile: 64.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

64.8% percentile inside its fair comparison set

46.1%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

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

Rank #102 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.4 /1M tokens
Percentile: 63.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

63.4% percentile inside its fair comparison set

$0.4 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #105 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.2 /1M input tokens
Percentile: 66.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

66.3% percentile inside its fair comparison set

$0.2 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #107 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.8 /1M output tokens
Percentile: 61.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

61.6% percentile inside its fair comparison set

$0.8 /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 #141 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 63.2 tokens/s
Percentile: 33.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33.3% percentile inside its fair comparison set

63.2 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #112 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.39s
Percentile: 47.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

47.1% percentile inside its fair comparison set

2.39sRaw 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 #66 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.39s
Percentile: 69%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

69% percentile inside its fair comparison set

2.39sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #76 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44
Percentile: 71%
Last updated: recent
Eligibility: benchmark_derived_model

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

71% percentile inside its fair comparison set

44Raw 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 #66

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 80%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: overall. Source rank: #84. Votes: 97241. Organization: alibaba. License: Apache 2.0.

80% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,421 - 1,426

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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 74.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: creative_writing. Source rank: #105. Votes: 13593. Organization: alibaba. License: Apache 2.0.

74.3% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,375 - 1,386

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 #74

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 77.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: english. Source rank: #92. Votes: 45078. Organization: alibaba. License: Apache 2.0.

77.5% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,427 - 1,434

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 #65

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: exclude_ties. Source rank: #83. Votes: 69277. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,411 - 1,419

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 #58

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 82.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts. Source rank: #74. Votes: 52312. Organization: alibaba. License: Apache 2.0.

82.5% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,445 - 1,451

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 #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 79.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts_english. Source rank: #84. Votes: 25618. Organization: alibaba. License: Apache 2.0.

79.6% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,447 - 1,455

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 #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 80.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: instruction_following. Source rank: #80. Votes: 26979. Organization: alibaba. License: Apache 2.0.

80.6% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,412 - 1,421

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 #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 79.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: longer_query. Source rank: #80. Votes: 25800. Organization: alibaba. License: Apache 2.0.

79.3% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,431 - 1,440

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 #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 83.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: multi_turn. Source rank: #71. Votes: 17023. Organization: alibaba. License: Apache 2.0.

83.6% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,433 - 1,443

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 #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 79.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: overall. Source rank: #80. Votes: 97241. Organization: alibaba. License: Apache 2.0.

79.7% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,417 - 1,422

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 #79

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 75.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: creative_writing. Source rank: #96. Votes: 13593. Organization: alibaba. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,371 - 1,382

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 #75

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 77.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: english. Source rank: #88. Votes: 45078. Organization: alibaba. License: Apache 2.0.

77.2% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,422 - 1,428

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 #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 79.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: exclude_ties. Source rank: #80. Votes: 69277. Organization: alibaba. License: Apache 2.0.

79.7% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,404 - 1,411

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 #52

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 84.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts. Source rank: #66. Votes: 52312. Organization: alibaba. License: Apache 2.0.

84.3% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,430 - 1,437

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 #61

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 81.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: hard_prompts_english. Source rank: #72. Votes: 25618. Organization: alibaba. License: Apache 2.0.

81.5% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,432 - 1,441

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 #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 83.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: instruction_following. Source rank: #68. Votes: 26979. Organization: alibaba. License: Apache 2.0.

83.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,405 - 1,413

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 #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 84.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: longer_query. Source rank: #60. Votes: 25800. Organization: alibaba. License: Apache 2.0.

84.5% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,423 - 1,432

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 #51

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 84.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: multi_turn. Source rank: #63. Votes: 17023. Organization: alibaba. License: Apache 2.0.

84.5% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,428 - 1,438

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 #97

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 21.7%
Percentile: 11.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

11.1% percentile inside its fair comparison set

21.7%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 #74

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.1%
Percentile: 32.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

32.4% percentile inside its fair comparison set

66.1%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 #93

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18%
Percentile: 14.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

14.8% percentile inside its fair comparison set

18%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 #95

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 21.9%
Percentile: 13%
Last updated: archived
Eligibility: benchmark_derived_model

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

13% percentile inside its fair comparison set

21.9%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 #98

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 19.4%
Percentile: 10.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

10.2% percentile inside its fair comparison set

19.4%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 #91

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 27.7%
Percentile: 16.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

16.7% percentile inside its fair comparison set

27.7%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 #50

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91%
Percentile: 57.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

57.4% percentile inside its fair comparison set

91%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 #86

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 39.2%
Percentile: 21.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

21.3% percentile inside its fair comparison set

39.2%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 #78

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 29.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

29.9% percentile inside its fair comparison set

68%Raw benchmark value

Coding11 benchmarks41%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #126 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.2%
Percentile: 59.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

59.3% percentile inside its fair comparison set

15.2%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #118 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36%
Percentile: 68.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

68.8% percentile inside its fair comparison set

36%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 #62

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: coding. Source rank: #78. Votes: 21307. Organization: alibaba. License: Apache 2.0.

80.9% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,469 - 1,478

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 #55

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 83.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: coding. Source rank: #66. Votes: 21307. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,441 - 1,450

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 #96

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 13.3%
Percentile: 12%
Last updated: archived
Eligibility: benchmark_derived_model

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

12% percentile inside its fair comparison set

13.3%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 #75

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.6%
Percentile: 31.5%
Last updated: archived
Eligibility: benchmark_derived_model

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

31.5% percentile inside its fair comparison set

69.6%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 #97

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 13.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

13.9% percentile inside its fair comparison set

10%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 #94

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 16.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

16.8% percentile inside its fair comparison set

10%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 #96

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20%
Percentile: 13.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

13.9% percentile inside its fair comparison set

20%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 #75

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.8%
Percentile: 35.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

35.2% percentile inside its fair comparison set

71.8%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 #77

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.4%
Percentile: 36.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

36.1% percentile inside its fair comparison set

67.4%Raw benchmark value

Reasoning / math / science15 benchmarks46.8%

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 #92 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 10.6%
Percentile: 75.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `hle`.

75.7% percentile inside its fair comparison set

10.6%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 #100 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.3%
Percentile: 73.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

73.5% percentile inside its fair comparison set

75.3%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 #284 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 79%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: math. Source rank: #85. Votes: 5924. Organization: alibaba. License: Apache 2.0.

79% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,412 - 1,428

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 #50

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 84.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: math. Source rank: #62. Votes: 5924. Organization: alibaba. License: Apache 2.0.

84.4% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,424 - 1,440

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #78

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 28.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

28.7% percentile inside its fair comparison set

68%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 #71

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.4%
Percentile: 35.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

35.2% percentile inside its fair comparison set

58.4%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 #92

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84%
Percentile: 16.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

16.7% percentile inside its fair comparison set

84%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 #80

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 21%
Percentile: 27.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

27.8% percentile inside its fair comparison set

21%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 #62

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.2%
Percentile: 46.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

46.3% percentile inside its fair comparison set

90.2%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 #80

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.9%
Percentile: 26.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

26.9% percentile inside its fair comparison set

76.9%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 #91

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.2%
Percentile: 17.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

17.6% percentile inside its fair comparison set

44.2%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 #61

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 43.5%
Percentile: 43.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

43.9% percentile inside its fair comparison set

43.5%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 #78

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84%
Percentile: 33.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

33.3% percentile inside its fair comparison set

84%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 #62

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62%
Percentile: 47.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

47.2% percentile inside its fair comparison set

62%Raw benchmark value

Professional reasoning23 benchmarks67.4%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #56

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 80%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: expert. Source rank: #73. Votes: 5893. Organization: alibaba. License: Apache 2.0.

80% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,444 - 1,460

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 #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 83.3%
Last updated: recent
Eligibility: benchmark_derived_model

83.3% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,427 - 1,437

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 #85

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 74%
Last updated: recent
Eligibility: benchmark_derived_model

74% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,373 - 1,382

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #65

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 78.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_legal_and_government. Source rank: #83. Votes: 6518. Organization: alibaba. License: Apache 2.0.

78.5% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,426 - 1,442

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 #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 80.5%
Last updated: recent
Eligibility: benchmark_derived_model

80.5% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,440 - 1,451

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #67

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 78.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_mathematical. Source rank: #82. Votes: 4926. Organization: alibaba. License: Apache 2.0.

78.6% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,424 - 1,442

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #53

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_medicine_and_healthcare. Source rank: #68. Votes: 5723. Organization: alibaba. License: Apache 2.0.

82.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,448 - 1,465

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 #61

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 81.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_software_and_it_services. Source rank: #77. Votes: 34735. Organization: alibaba. License: Apache 2.0.

81.5% percentile inside its fair comparison set

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

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 #77

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 76.5%
Last updated: recent
Eligibility: benchmark_derived_model

76.5% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,393 - 1,402

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #45

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 84%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: expert. Source rank: #53. Votes: 5893. Organization: alibaba. License: Apache 2.0.

84% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,437 - 1,453

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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model

82.4% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,413 - 1,423

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 #80

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 75.5%
Last updated: recent
Eligibility: benchmark_derived_model

75.5% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,370 - 1,380

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 #63

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 79.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_legal_and_government. Source rank: #76. Votes: 6518. Organization: alibaba. License: Apache 2.0.

79.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,422 - 1,437

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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 82.7%
Last updated: recent
Eligibility: benchmark_derived_model

82.7% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,433 - 1,444

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #44

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 86%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_mathematical. Source rank: #52. Votes: 4926. Organization: alibaba. License: Apache 2.0.

86% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,432 - 1,450

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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 81%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_medicine_and_healthcare. Source rank: #65. Votes: 5723. Organization: alibaba. License: Apache 2.0.

81% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,437 - 1,454

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 #56

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 83.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: industry_software_and_it_services. Source rank: #69. Votes: 34735. Organization: alibaba. License: Apache 2.0.

83.1% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,442 - 1,450

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 #74

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 77.5%
Last updated: recent
Eligibility: benchmark_derived_model

77.5% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,386 - 1,395

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #92

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.7%
Percentile: 15.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

15.7% percentile inside its fair comparison set

44.7%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #87

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.8%
Percentile: 20.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

20.4% percentile inside its fair comparison set

48.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #85

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 3.7%
Percentile: 22.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

22.2% percentile inside its fair comparison set

3.7%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #93

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 34.4%
Percentile: 14.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

14.8% percentile inside its fair comparison set

34.4%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #88

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 30.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

30.6% percentile inside its fair comparison set

96.1%Raw benchmark value

Search / tool use1 benchmark47.2%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #164 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.3%
Percentile: 47.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

47.2% percentile inside its fair comparison set

33.3%Raw benchmark value

Long context1 benchmark52.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #150 · Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.2%
Percentile: 52.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

52.7% percentile inside its fair comparison set

31.2%Raw benchmark value

Multilingual14 benchmarks79.2%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #59

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: chinese. Source rank: #72. Votes: 4967. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,463 - 1,481

Text Arena · French

AR · Multilingual · Human

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

Rank #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 78.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: french. Source rank: #62. Votes: 1989. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,445 - 1,475

Text Arena · German

AR · Multilingual · Human

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

Rank #51

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 78.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: german. Source rank: #68. Votes: 1711. Organization: alibaba. License: Apache 2.0.

78.9% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,413 - 1,443

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 76.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: japanese. Source rank: #65. Votes: 1261. Organization: alibaba. License: Apache 2.0.

76.8% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,364 - 1,399

Text Arena · Korean

AR · Multilingual · Human

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

Rank #50

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 76.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: korean. Source rank: #64. Votes: 1731. Organization: alibaba. License: Apache 2.0.

76.4% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,368 - 1,399

Text Arena · Russian

AR · Multilingual · Human

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

Rank #60

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 79.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: russian. Source rank: #79. Votes: 8460. Organization: alibaba. License: Apache 2.0.

79.6% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,410 - 1,424

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #55

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 74.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: spanish. Source rank: #68. Votes: 2564. Organization: alibaba. License: Apache 2.0.

74.8% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,410 - 1,437

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #53

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: chinese. Source rank: #63. Votes: 4967. Organization: alibaba. License: Apache 2.0.

82.4% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,457 - 1,475

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #46

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 79.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: french. Source rank: #54. Votes: 1989. Organization: alibaba. License: Apache 2.0.

79.2% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,436 - 1,466

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #30

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 87.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: german. Source rank: #38. Votes: 1711. Organization: alibaba. License: Apache 2.0.

87.8% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,422 - 1,451

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #41

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: japanese. Source rank: #53. Votes: 1261. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,371 - 1,406

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #42

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: korean. Source rank: #51. Votes: 1731. Organization: alibaba. License: Apache 2.0.

80.3% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,377 - 1,408

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 78.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: russian. Source rank: #80. Votes: 8460. Organization: alibaba. License: Apache 2.0.

78.2% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,404 - 1,417

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 75.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `qwen3-235b-a22b-instruct-2507`. Category: spanish. Source rank: #65. Votes: 2564. Organization: alibaba. License: Apache 2.0.

75.2% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,412 - 1,438