Model profile · DeepSeek

DeepSeek V3.2 Exp

Open weightsbudget · registry tag 2026 preview

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 33.6%
Verified coverage: 33.6%
Spread: n/a
Last verified: Jun 20, 2026

textcodedocument7 aliases32 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text35 benchmarks61.4%

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 #112 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 21
Percentile: 71.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

71.9% percentile inside its fair comparison set

21Raw 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 #84 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22.7%
Percentile: 72.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

72.1% percentile inside its fair comparison set

22.7%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

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

Rank #218 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9.7%
Percentile: 27.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

27.2% percentile inside its fair comparison set

9.7%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 #140 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.1%
Percentile: 55.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

55.9% percentile inside its fair comparison set

43.1%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 #95 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M tokens
Percentile: 65.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

65.9% percentile inside its fair comparison set

$0.3 /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 #118 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M input tokens
Percentile: 57.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

57.6% percentile inside its fair comparison set

$0.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #79 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.4 /1M output tokens
Percentile: 71.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

71.7% percentile inside its fair comparison set

$0.4 /1M output tokensRaw 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 #71 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44
Percentile: 71%
Last updated: recent
Eligibility: preview_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 #67 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 79.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: overall. Source rank: #85. Votes: 11922. Organization: deepseek. License: MIT.

79.7% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,417 - 1,429

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 #45 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 86.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: creative_writing. Source rank: #58. Votes: 1628. Organization: deepseek. License: MIT.

86.4% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,396 - 1,425

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 #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: english. Source rank: #79. Votes: 5676. Organization: deepseek. License: MIT.

80.9% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,429 - 1,446

Text Arena · Exclude Ties

AR · Chat / text · Human

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

Rank #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: exclude_ties. Source rank: #80. Votes: 8383. Organization: deepseek. License: MIT.

80.9% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,407 - 1,425

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts. Source rank: #76. Votes: 6464. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 1,456

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 #65 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts_english. Source rank: #81. Votes: 3206. Organization: deepseek. License: MIT.

80.2% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,443 - 1,464

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 #62 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 81.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: instruction_following. Source rank: #78. Votes: 3310. Organization: deepseek. License: MIT.

81.2% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,406 - 1,427

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 #55 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: longer_query. Source rank: #69. Votes: 2933. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

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

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: multi_turn. Source rank: #76. Votes: 1984. Organization: deepseek. License: MIT.

82% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,418 - 1,444

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 #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 82.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: overall. Source rank: #69. Votes: 11922. Organization: deepseek. License: MIT.

82.8% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,416 - 1,429

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 #46 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: creative_writing. Source rank: #59. Votes: 1628. Organization: deepseek. License: MIT.

86.1% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,390 - 1,419

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 #52 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 84.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: english. Source rank: #64. Votes: 5676. Organization: deepseek. License: MIT.

84.3% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,431 - 1,448

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

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

Rank #55 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 83.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: exclude_ties. Source rank: #67. Votes: 8383. Organization: deepseek. License: MIT.

83.4% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,423

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts. Source rank: #73. Votes: 6464. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,422 - 1,438

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 #60 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 81.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts_english. Source rank: #71. Votes: 3206. Organization: deepseek. License: MIT.

81.8% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,428 - 1,449

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 #67 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 79.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: instruction_following. Source rank: #81. Votes: 3310. Organization: deepseek. License: MIT.

79.7% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,392 - 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 #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 79.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: longer_query. Source rank: #76. Votes: 2933. Organization: deepseek. License: MIT.

79.6% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,408 - 1,429

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: multi_turn. Source rank: #73. Votes: 1984. Organization: deepseek. License: MIT.

82% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,411 - 1,437

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 #100 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 19.3%
Percentile: 8.3%
Last updated: archived
Eligibility: preview_model

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

8.3% percentile inside its fair comparison set

19.3%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 #75 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.6%
Percentile: 31.5%
Last updated: archived
Eligibility: preview_model

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

31.5% percentile inside its fair comparison set

65.6%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 #101 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.1%
Percentile: 7.4%
Last updated: archived
Eligibility: preview_model

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

7.4% percentile inside its fair comparison set

16.1%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 #96 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.9%
Percentile: 12%
Last updated: archived
Eligibility: preview_model

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

12% percentile inside its fair comparison set

20.9%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 #103 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.7%
Percentile: 5.6%
Last updated: archived
Eligibility: preview_model

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

5.6% percentile inside its fair comparison set

16.7%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 #99 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 23.7%
Percentile: 9.3%
Last updated: archived
Eligibility: preview_model

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

9.3% percentile inside its fair comparison set

23.7%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 #77 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.3%
Percentile: 29.6%
Last updated: archived
Eligibility: preview_model

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

29.6% percentile inside its fair comparison set

79.3%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 #74 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.5%
Percentile: 32.4%
Last updated: archived
Eligibility: preview_model

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

32.4% percentile inside its fair comparison set

45.5%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #67 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72%
Percentile: 41.1%
Last updated: archived
Eligibility: preview_model

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

41.1% percentile inside its fair comparison set

72%Raw benchmark value

Coding14 benchmarks47.7%

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 #83 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25%
Percentile: 72.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

72.8% percentile inside its fair comparison set

25%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 #87 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 37.7%
Percentile: 76.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

76.6% percentile inside its fair comparison set

37.7%Raw benchmark value

Code Arena

AR · Coding · Human

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

Rank #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 23.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: overall. Source rank: #72. Votes: 4873. Organization: deepseek. License: MIT.

23.3% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,276 - 1,298

WebDev Arena

AR · Coding · Human

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

Rank #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 23.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: webdev. Source rank: #72. Votes: 4873. Organization: deepseek. License: MIT.

23.3% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,276 - 1,298

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #60 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,295
Percentile: 19.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: webdev-html. Source rank: #73. Votes: 4873. Organization: deepseek. License: MIT.

19.2% percentile inside its fair comparison set

1,295Raw benchmark valueCI 1,283 - 1,307

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 #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 78.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: coding. Source rank: #87. Votes: 2499. Organization: deepseek. License: MIT.

78.4% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,454 - 1,477

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 #71 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 78.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: coding. Source rank: #87. Votes: 2499. Organization: deepseek. License: MIT.

78.1% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,422 - 1,446

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 #75 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 36.7%
Percentile: 31.5%
Last updated: archived
Eligibility: preview_model

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

31.5% percentile inside its fair comparison set

36.7%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 #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 48.1%
Last updated: archived
Eligibility: preview_model

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

48.1% percentile inside its fair comparison set

73.2%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 #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 30%
Percentile: 38%
Last updated: archived
Eligibility: preview_model

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

38% percentile inside its fair comparison set

30%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 #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25%
Percentile: 37.4%
Last updated: archived
Eligibility: preview_model

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

37.4% percentile inside its fair comparison set

25%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 #69 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55%
Percentile: 37%
Last updated: archived
Eligibility: preview_model

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

37% percentile inside its fair comparison set

55%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 #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 52.8%
Last updated: archived
Eligibility: preview_model

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

52.8% percentile inside its fair comparison set

74.6%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 #54 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.7%
Percentile: 50.9%
Last updated: archived
Eligibility: preview_model

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

50.9% percentile inside its fair comparison set

71.7%Raw benchmark value

Reasoning / math / science15 benchmarks41.4%

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 #118 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 8.6%
Percentile: 68.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

68.4% percentile inside its fair comparison set

8.6%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 #113 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 73.8%
Percentile: 70.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

70.1% percentile inside its fair comparison set

73.8%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 #41 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.4%
Percentile: 88.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

88.1% percentile inside its fair comparison set

1.4%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 78%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: math. Source rank: #88. Votes: 775. Organization: deepseek. License: MIT.

78% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,397 - 1,439

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 #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 80.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: math. Source rank: #75. Votes: 775. Organization: deepseek. License: MIT.

80.3% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,403 - 1,444

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #85 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.4%
Percentile: 22.2%
Last updated: archived
Eligibility: preview_model

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

22.2% percentile inside its fair comparison set

64.4%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 #82 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.5%
Percentile: 25%
Last updated: archived
Eligibility: preview_model

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

25% percentile inside its fair comparison set

45.5%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 #72 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92%
Percentile: 34.3%
Last updated: archived
Eligibility: preview_model

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

34.3% percentile inside its fair comparison set

92%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 #83 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 13%
Percentile: 24.1%
Last updated: archived
Eligibility: preview_model

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

24.1% percentile inside its fair comparison set

13%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 #92 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.5%
Percentile: 15.7%
Last updated: archived
Eligibility: preview_model

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

15.7% percentile inside its fair comparison set

75.5%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 #79 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77%
Percentile: 27.8%
Last updated: archived
Eligibility: preview_model

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

27.8% percentile inside its fair comparison set

77%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 #82 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 27.8%
Last updated: archived
Eligibility: preview_model

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

27.8% percentile inside its fair comparison set

50%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 #93 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 12%
Percentile: 14%
Last updated: archived
Eligibility: preview_model

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

14% percentile inside its fair comparison set

12%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 #84 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 24.1%
Last updated: archived
Eligibility: preview_model

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

24.1% percentile inside its fair comparison set

80%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 #86 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 40%
Percentile: 21.3%
Last updated: archived
Eligibility: preview_model

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

21.3% percentile inside its fair comparison set

40%Raw benchmark value

Professional reasoning23 benchmarks66.3%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #87 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 68.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: expert. Source rank: #107. Votes: 609. Organization: deepseek. License: MIT.

68.7% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,399 - 1,446

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 #62 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 80.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_business_and_management_and_financial_operations. Source rank: #78. Votes: 2208. Organization: deepseek. License: MIT.

80.8% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,410 - 1,435

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 #48 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 85.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_entertainment_and_sports_and_media. Source rank: #60. Votes: 2156. Organization: deepseek. License: MIT.

85.4% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,395 - 1,420

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #85 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 71.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_legal_and_government. Source rank: #107. Votes: 782. Organization: deepseek. License: MIT.

71.8% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,395 - 1,437

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

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

Rank #76 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 76.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_life_and_physical_and_social_science. Source rank: #94. Votes: 1910. Organization: deepseek. License: MIT.

76.8% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,421 - 1,448

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #91 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 70.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_mathematical. Source rank: #109. Votes: 633. Organization: deepseek. License: MIT.

70.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,390 - 1,435

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #78 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_medicine_and_healthcare. Source rank: #96. Votes: 583. Organization: deepseek. License: MIT.

73.9% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,412 - 1,460

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 #74 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 77.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_software_and_it_services. Source rank: #91. Votes: 4132. Organization: deepseek. License: MIT.

77.5% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,444 - 1,463

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 #51 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 84.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_writing_and_literature_and_language. Source rank: #65. Votes: 2602. Organization: deepseek. License: MIT.

84.6% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,402 - 1,425

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #92 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 66.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: expert. Source rank: #112. Votes: 609. Organization: deepseek. License: MIT.

66.9% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,377 - 1,424

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 #62 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 80.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_business_and_management_and_financial_operations. Source rank: #76. Votes: 2208. Organization: deepseek. License: MIT.

80.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,401 - 1,426

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 #40 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 87.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_entertainment_and_sports_and_media. Source rank: #51. Votes: 2156. Organization: deepseek. License: MIT.

87.9% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,392 - 1,417

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 #88 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 70.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_legal_and_government. Source rank: #107. Votes: 782. Organization: deepseek. License: MIT.

70.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,388 - 1,430

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 #76 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 76.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_life_and_physical_and_social_science. Source rank: #90. Votes: 1910. Organization: deepseek. License: MIT.

76.8% percentile inside its fair comparison set

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

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #82 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 73.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_mathematical. Source rank: #99. Votes: 633. Organization: deepseek. License: MIT.

73.7% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,392 - 1,437

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 #72 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 75.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_medicine_and_healthcare. Source rank: #84. Votes: 583. Organization: deepseek. License: MIT.

75.9% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,405 - 1,452

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 #74 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 77.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_software_and_it_services. Source rank: #89. Votes: 4132. Organization: deepseek. License: MIT.

77.5% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,426 - 1,445

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 #49 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 85.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_writing_and_literature_and_language. Source rank: #61. Votes: 2602. Organization: deepseek. License: MIT.

85.2% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,398 - 1,421

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #93 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.3%
Percentile: 14.8%
Last updated: archived
Eligibility: preview_model

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

14.8% percentile inside its fair comparison set

44.3%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #83 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 49.8%
Percentile: 24.1%
Last updated: archived
Eligibility: preview_model

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

24.1% percentile inside its fair comparison set

49.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #93 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 2.6%
Percentile: 14.8%
Last updated: archived
Eligibility: preview_model

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

14.8% percentile inside its fair comparison set

2.6%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #98 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 32.1%
Percentile: 10.2%
Last updated: archived
Eligibility: preview_model

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

10.2% percentile inside its fair comparison set

32.1%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #49 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 74.1%
Last updated: archived
Eligibility: preview_model

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

74.1% percentile inside its fair comparison set

98%Raw benchmark value

Search / tool use1 benchmark47.6%

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 #163 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.9%
Percentile: 47.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

47.6% percentile inside its fair comparison set

33.9%Raw benchmark value

Long context1 benchmark64.1%

Long Context Reasoning

AA · Long context · Objective

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

Rank #114 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 64.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

64.1% percentile inside its fair comparison set

43%Raw benchmark value

Multilingual14 benchmarks75.6%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #54 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: chinese. Source rank: #66. Votes: 624. Organization: deepseek. License: MIT.

82% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,453 - 1,498

Text Arena · French

AR · Multilingual · Human

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

Rank #56 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 74.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: french. Source rank: #71. Votes: 198. Organization: deepseek. License: MIT.

74.5% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,407 - 1,492

Text Arena · German

AR · Multilingual · Human

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

Rank #37 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 84.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: german. Source rank: #49. Votes: 210. Organization: deepseek. License: MIT.

84.8% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,402 - 1,480

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #75 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 63.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: japanese. Source rank: #95. Votes: 120. Organization: deepseek. License: MIT.

63.5% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,293 - 1,401

Text Arena · Korean

AR · Multilingual · Human

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

Rank #61 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 71.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: korean. Source rank: #78. Votes: 193. Organization: deepseek. License: MIT.

71.2% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,329 - 1,413

Text Arena · Russian

AR · Multilingual · Human

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

Rank #80 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: russian. Source rank: #99. Votes: 844. Organization: deepseek. License: MIT.

72.7% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,386 - 1,425

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #44 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 79.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: spanish. Source rank: #56. Votes: 301. Organization: deepseek. License: MIT.

79.9% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,404 - 1,472

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #58 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 80.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: chinese. Source rank: #69. Votes: 624. Organization: deepseek. License: MIT.

80.7% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,441 - 1,487

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #55 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: french. Source rank: #67. Votes: 198. Organization: deepseek. License: MIT.

75% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,397 - 1,482

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #34 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: german. Source rank: #43. Votes: 210. Organization: deepseek. License: MIT.

86.1% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,395 - 1,473

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #80 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,328
Percentile: 61.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: japanese. Source rank: #100. Votes: 120. Organization: deepseek. License: MIT.

61.1% percentile inside its fair comparison set

1,328Raw benchmark valueCI 1,272 - 1,383

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #66 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 68.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: korean. Source rank: #80. Votes: 193. Organization: deepseek. License: MIT.

68.8% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,322 - 1,406

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 76.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: russian. Source rank: #87. Votes: 844. Organization: deepseek. License: MIT.

76.1% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,385 - 1,424

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #39 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: spanish. Source rank: #47. Votes: 301. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,407 - 1,475

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

Model profile · DeepSeek

DeepSeek V3.2 Exp

Open weightsbudget · registry tag 2026 preview

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 33.6%
Verified coverage: 33.6%
Spread: n/a
Last verified: Jun 20, 2026

textcodedocument7 aliases32 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text35 benchmarks61.4%

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 #112 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 21
Percentile: 71.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

71.9% percentile inside its fair comparison set

21Raw 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 #84 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22.7%
Percentile: 72.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

72.1% percentile inside its fair comparison set

22.7%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

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

Rank #218 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9.7%
Percentile: 27.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

27.2% percentile inside its fair comparison set

9.7%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 #140 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.1%
Percentile: 55.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

55.9% percentile inside its fair comparison set

43.1%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 #95 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M tokens
Percentile: 65.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

65.9% percentile inside its fair comparison set

$0.3 /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 #118 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M input tokens
Percentile: 57.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

57.6% percentile inside its fair comparison set

$0.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #79 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.4 /1M output tokens
Percentile: 71.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

71.7% percentile inside its fair comparison set

$0.4 /1M output tokensRaw 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 #71 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44
Percentile: 71%
Last updated: recent
Eligibility: preview_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 #67 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 79.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: overall. Source rank: #85. Votes: 11922. Organization: deepseek. License: MIT.

79.7% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,417 - 1,429

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 #45 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 86.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: creative_writing. Source rank: #58. Votes: 1628. Organization: deepseek. License: MIT.

86.4% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,396 - 1,425

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 #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: english. Source rank: #79. Votes: 5676. Organization: deepseek. License: MIT.

80.9% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,429 - 1,446

Text Arena · Exclude Ties

AR · Chat / text · Human

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

Rank #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: exclude_ties. Source rank: #80. Votes: 8383. Organization: deepseek. License: MIT.

80.9% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,407 - 1,425

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts. Source rank: #76. Votes: 6464. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 1,456

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 #65 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts_english. Source rank: #81. Votes: 3206. Organization: deepseek. License: MIT.

80.2% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,443 - 1,464

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 #62 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 81.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: instruction_following. Source rank: #78. Votes: 3310. Organization: deepseek. License: MIT.

81.2% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,406 - 1,427

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 #55 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 82.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: longer_query. Source rank: #69. Votes: 2933. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

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

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: multi_turn. Source rank: #76. Votes: 1984. Organization: deepseek. License: MIT.

82% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,418 - 1,444

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 #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 82.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: overall. Source rank: #69. Votes: 11922. Organization: deepseek. License: MIT.

82.8% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,416 - 1,429

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 #46 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: creative_writing. Source rank: #59. Votes: 1628. Organization: deepseek. License: MIT.

86.1% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,390 - 1,419

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 #52 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 84.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: english. Source rank: #64. Votes: 5676. Organization: deepseek. License: MIT.

84.3% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,431 - 1,448

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

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

Rank #55 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 83.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: exclude_ties. Source rank: #67. Votes: 8383. Organization: deepseek. License: MIT.

83.4% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,423

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts. Source rank: #73. Votes: 6464. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,422 - 1,438

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 #60 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 81.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: hard_prompts_english. Source rank: #71. Votes: 3206. Organization: deepseek. License: MIT.

81.8% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,428 - 1,449

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 #67 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 79.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: instruction_following. Source rank: #81. Votes: 3310. Organization: deepseek. License: MIT.

79.7% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,392 - 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 #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 79.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: longer_query. Source rank: #76. Votes: 2933. Organization: deepseek. License: MIT.

79.6% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,408 - 1,429

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 #59 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: multi_turn. Source rank: #73. Votes: 1984. Organization: deepseek. License: MIT.

82% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,411 - 1,437

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 #100 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 19.3%
Percentile: 8.3%
Last updated: archived
Eligibility: preview_model

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

8.3% percentile inside its fair comparison set

19.3%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 #75 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.6%
Percentile: 31.5%
Last updated: archived
Eligibility: preview_model

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

31.5% percentile inside its fair comparison set

65.6%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 #101 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.1%
Percentile: 7.4%
Last updated: archived
Eligibility: preview_model

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

7.4% percentile inside its fair comparison set

16.1%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 #96 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.9%
Percentile: 12%
Last updated: archived
Eligibility: preview_model

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

12% percentile inside its fair comparison set

20.9%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 #103 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.7%
Percentile: 5.6%
Last updated: archived
Eligibility: preview_model

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

5.6% percentile inside its fair comparison set

16.7%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 #99 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 23.7%
Percentile: 9.3%
Last updated: archived
Eligibility: preview_model

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

9.3% percentile inside its fair comparison set

23.7%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 #77 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.3%
Percentile: 29.6%
Last updated: archived
Eligibility: preview_model

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

29.6% percentile inside its fair comparison set

79.3%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 #74 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.5%
Percentile: 32.4%
Last updated: archived
Eligibility: preview_model

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

32.4% percentile inside its fair comparison set

45.5%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #67 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72%
Percentile: 41.1%
Last updated: archived
Eligibility: preview_model

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

41.1% percentile inside its fair comparison set

72%Raw benchmark value

Coding14 benchmarks47.7%

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 #83 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25%
Percentile: 72.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

72.8% percentile inside its fair comparison set

25%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 #87 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 37.7%
Percentile: 76.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

76.6% percentile inside its fair comparison set

37.7%Raw benchmark value

Code Arena

AR · Coding · Human

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

Rank #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 23.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: overall. Source rank: #72. Votes: 4873. Organization: deepseek. License: MIT.

23.3% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,276 - 1,298

WebDev Arena

AR · Coding · Human

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

Rank #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 23.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: webdev. Source rank: #72. Votes: 4873. Organization: deepseek. License: MIT.

23.3% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,276 - 1,298

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #60 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,295
Percentile: 19.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: webdev-html. Source rank: #73. Votes: 4873. Organization: deepseek. License: MIT.

19.2% percentile inside its fair comparison set

1,295Raw benchmark valueCI 1,283 - 1,307

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 #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 78.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: coding. Source rank: #87. Votes: 2499. Organization: deepseek. License: MIT.

78.4% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,454 - 1,477

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 #71 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 78.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: coding. Source rank: #87. Votes: 2499. Organization: deepseek. License: MIT.

78.1% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,422 - 1,446

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 #75 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 36.7%
Percentile: 31.5%
Last updated: archived
Eligibility: preview_model

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

31.5% percentile inside its fair comparison set

36.7%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 #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 48.1%
Last updated: archived
Eligibility: preview_model

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

48.1% percentile inside its fair comparison set

73.2%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 #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 30%
Percentile: 38%
Last updated: archived
Eligibility: preview_model

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

38% percentile inside its fair comparison set

30%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 #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25%
Percentile: 37.4%
Last updated: archived
Eligibility: preview_model

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

37.4% percentile inside its fair comparison set

25%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 #69 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55%
Percentile: 37%
Last updated: archived
Eligibility: preview_model

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

37% percentile inside its fair comparison set

55%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 #57 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 52.8%
Last updated: archived
Eligibility: preview_model

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

52.8% percentile inside its fair comparison set

74.6%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 #54 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.7%
Percentile: 50.9%
Last updated: archived
Eligibility: preview_model

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

50.9% percentile inside its fair comparison set

71.7%Raw benchmark value

Reasoning / math / science15 benchmarks41.4%

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 #118 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 8.6%
Percentile: 68.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

68.4% percentile inside its fair comparison set

8.6%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 #113 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 73.8%
Percentile: 70.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

70.1% percentile inside its fair comparison set

73.8%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 #41 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.4%
Percentile: 88.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

88.1% percentile inside its fair comparison set

1.4%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 78%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: math. Source rank: #88. Votes: 775. Organization: deepseek. License: MIT.

78% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,397 - 1,439

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 #63 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 80.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: math. Source rank: #75. Votes: 775. Organization: deepseek. License: MIT.

80.3% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,403 - 1,444

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #85 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.4%
Percentile: 22.2%
Last updated: archived
Eligibility: preview_model

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

22.2% percentile inside its fair comparison set

64.4%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 #82 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.5%
Percentile: 25%
Last updated: archived
Eligibility: preview_model

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

25% percentile inside its fair comparison set

45.5%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 #72 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92%
Percentile: 34.3%
Last updated: archived
Eligibility: preview_model

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

34.3% percentile inside its fair comparison set

92%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 #83 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 13%
Percentile: 24.1%
Last updated: archived
Eligibility: preview_model

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

24.1% percentile inside its fair comparison set

13%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 #92 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.5%
Percentile: 15.7%
Last updated: archived
Eligibility: preview_model

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

15.7% percentile inside its fair comparison set

75.5%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 #79 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77%
Percentile: 27.8%
Last updated: archived
Eligibility: preview_model

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

27.8% percentile inside its fair comparison set

77%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 #82 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 27.8%
Last updated: archived
Eligibility: preview_model

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

27.8% percentile inside its fair comparison set

50%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 #93 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 12%
Percentile: 14%
Last updated: archived
Eligibility: preview_model

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

14% percentile inside its fair comparison set

12%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 #84 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 24.1%
Last updated: archived
Eligibility: preview_model

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

24.1% percentile inside its fair comparison set

80%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 #86 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 40%
Percentile: 21.3%
Last updated: archived
Eligibility: preview_model

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

21.3% percentile inside its fair comparison set

40%Raw benchmark value

Professional reasoning23 benchmarks66.3%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #87 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 68.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: expert. Source rank: #107. Votes: 609. Organization: deepseek. License: MIT.

68.7% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,399 - 1,446

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 #62 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 80.8%
Last updated: recent
Eligibility: preview_model

80.8% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,410 - 1,435

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 #48 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 85.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_entertainment_and_sports_and_media. Source rank: #60. Votes: 2156. Organization: deepseek. License: MIT.

85.4% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,395 - 1,420

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #85 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 71.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_legal_and_government. Source rank: #107. Votes: 782. Organization: deepseek. License: MIT.

71.8% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,395 - 1,437

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

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

Rank #76 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 76.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_life_and_physical_and_social_science. Source rank: #94. Votes: 1910. Organization: deepseek. License: MIT.

76.8% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,421 - 1,448

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #91 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 70.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_mathematical. Source rank: #109. Votes: 633. Organization: deepseek. License: MIT.

70.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,390 - 1,435

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #78 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 73.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_medicine_and_healthcare. Source rank: #96. Votes: 583. Organization: deepseek. License: MIT.

73.9% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,412 - 1,460

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 #74 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 77.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_software_and_it_services. Source rank: #91. Votes: 4132. Organization: deepseek. License: MIT.

77.5% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,444 - 1,463

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 #51 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 84.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_writing_and_literature_and_language. Source rank: #65. Votes: 2602. Organization: deepseek. License: MIT.

84.6% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,402 - 1,425

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #92 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 66.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: expert. Source rank: #112. Votes: 609. Organization: deepseek. License: MIT.

66.9% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,377 - 1,424

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 #62 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 80.8%
Last updated: recent
Eligibility: preview_model

80.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,401 - 1,426

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 #40 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 87.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_entertainment_and_sports_and_media. Source rank: #51. Votes: 2156. Organization: deepseek. License: MIT.

87.9% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,392 - 1,417

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 #88 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 70.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_legal_and_government. Source rank: #107. Votes: 782. Organization: deepseek. License: MIT.

70.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,388 - 1,430

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 #76 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 76.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_life_and_physical_and_social_science. Source rank: #90. Votes: 1910. Organization: deepseek. License: MIT.

76.8% percentile inside its fair comparison set

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

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #82 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 73.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_mathematical. Source rank: #99. Votes: 633. Organization: deepseek. License: MIT.

73.7% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,392 - 1,437

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 #72 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 75.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_medicine_and_healthcare. Source rank: #84. Votes: 583. Organization: deepseek. License: MIT.

75.9% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,405 - 1,452

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 #74 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 77.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_software_and_it_services. Source rank: #89. Votes: 4132. Organization: deepseek. License: MIT.

77.5% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,426 - 1,445

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 #49 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 85.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: industry_writing_and_literature_and_language. Source rank: #61. Votes: 2602. Organization: deepseek. License: MIT.

85.2% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,398 - 1,421

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #93 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.3%
Percentile: 14.8%
Last updated: archived
Eligibility: preview_model

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

14.8% percentile inside its fair comparison set

44.3%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #83 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 49.8%
Percentile: 24.1%
Last updated: archived
Eligibility: preview_model

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

24.1% percentile inside its fair comparison set

49.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #93 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 2.6%
Percentile: 14.8%
Last updated: archived
Eligibility: preview_model

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

14.8% percentile inside its fair comparison set

2.6%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #98 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 32.1%
Percentile: 10.2%
Last updated: archived
Eligibility: preview_model

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

10.2% percentile inside its fair comparison set

32.1%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #49 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 74.1%
Last updated: archived
Eligibility: preview_model

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

74.1% percentile inside its fair comparison set

98%Raw benchmark value

Search / tool use1 benchmark47.6%

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 #163 · Source label: DeepSeek V3.2 Exp (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.9%
Percentile: 47.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

47.6% percentile inside its fair comparison set

33.9%Raw benchmark value

Long context1 benchmark64.1%

Long Context Reasoning

AA · Long context · Objective

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

Rank #114 · Source label: DeepSeek V3.2 Exp (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 64.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

64.1% percentile inside its fair comparison set

43%Raw benchmark value

Multilingual14 benchmarks75.6%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #54 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: chinese. Source rank: #66. Votes: 624. Organization: deepseek. License: MIT.

82% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,453 - 1,498

Text Arena · French

AR · Multilingual · Human

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

Rank #56 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 74.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: french. Source rank: #71. Votes: 198. Organization: deepseek. License: MIT.

74.5% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,407 - 1,492

Text Arena · German

AR · Multilingual · Human

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

Rank #37 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 84.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: german. Source rank: #49. Votes: 210. Organization: deepseek. License: MIT.

84.8% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,402 - 1,480

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #75 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 63.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: japanese. Source rank: #95. Votes: 120. Organization: deepseek. License: MIT.

63.5% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,293 - 1,401

Text Arena · Korean

AR · Multilingual · Human

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

Rank #61 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 71.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: korean. Source rank: #78. Votes: 193. Organization: deepseek. License: MIT.

71.2% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,329 - 1,413

Text Arena · Russian

AR · Multilingual · Human

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

Rank #80 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: russian. Source rank: #99. Votes: 844. Organization: deepseek. License: MIT.

72.7% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,386 - 1,425

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #44 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 79.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: spanish. Source rank: #56. Votes: 301. Organization: deepseek. License: MIT.

79.9% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,404 - 1,472

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #58 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 80.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: chinese. Source rank: #69. Votes: 624. Organization: deepseek. License: MIT.

80.7% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,441 - 1,487

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #55 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: french. Source rank: #67. Votes: 198. Organization: deepseek. License: MIT.

75% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,397 - 1,482

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #34 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: german. Source rank: #43. Votes: 210. Organization: deepseek. License: MIT.

86.1% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,395 - 1,473

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #80 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,328
Percentile: 61.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: japanese. Source rank: #100. Votes: 120. Organization: deepseek. License: MIT.

61.1% percentile inside its fair comparison set

1,328Raw benchmark valueCI 1,272 - 1,383

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #66 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 68.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: korean. Source rank: #80. Votes: 193. Organization: deepseek. License: MIT.

68.8% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,322 - 1,406

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #70 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 76.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: russian. Source rank: #87. Votes: 844. Organization: deepseek. License: MIT.

76.1% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,385 - 1,424

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #39 · Source label: deepseek-v3.2-exp

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `deepseek-v3.2-exp`. Category: spanish. Source rank: #47. Votes: 301. Organization: deepseek. License: MIT.

82.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,407 - 1,475

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

DeepSeek V3.2 Exp

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

DeepSeek V3.2 Exp

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks