Model profile · Zhipu

glm-5.2-max

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

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

Visible coverage: 46.6%
Verified coverage: 46.6%
Spread: 92.3%
Last verified: Oct 3, 2026

69%capability fit

textcodedocument7 aliases35 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text36 benchmarks67.6%

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 #144 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

74.2% percentile inside its fair comparison set

22Raw 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 #225 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 20.3%
Percentile: 50.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

50.6% percentile inside its fair comparison set

20.3%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 #48 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 66.3%
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

89.6% percentile inside its fair comparison set

66.3%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 #19 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 73.3%
Percentile: 94.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

94.8% percentile inside its fair comparison set

73.3%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #253 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.4 /1M input tokens
Percentile: 29.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

29.4% percentile inside its fair comparison set

$1.4 /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 #242 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $4.4 /1M output tokens
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

33.3% percentile inside its fair comparison set

$4.4 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

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

Rank #135 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 84.2 tokens/s
Percentile: 48.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.9% percentile inside its fair comparison set

84.2 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #146 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.10s
Percentile: 45.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

45.1% percentile inside its fair comparison set

3.10sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

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

Rank #164 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 26.85s
Percentile: 37.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

37.8% percentile inside its fair comparison set

26.85sRaw 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 #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: overall. Source rank: #32. Votes: 45399. Organization: zai. License: MIT.

92.3% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,471 - 1,480

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 #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: creative_writing. Source rank: #32. Votes: 8979. Organization: zai. License: MIT.

92% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,447 - 1,462

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 #32 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: english. Source rank: #33. Votes: 18859. Organization: zai. License: MIT.

91.8% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,477 - 1,488

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 #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: exclude_ties. Source rank: #33. Votes: 33697. Organization: zai. License: MIT.

92% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,480 - 1,491

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 #39 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 89.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts. Source rank: #40. Votes: 29821. Organization: zai. License: MIT.

89.9% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,491 - 1,501

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 #39 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts_english. Source rank: #40. Votes: 12565. Organization: zai. License: MIT.

89.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,491 - 1,503

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 #36 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: instruction_following. Source rank: #37. Votes: 15855. Organization: zai. License: MIT.

90.7% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,464 - 1,475

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 #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 91.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: longer_query. Source rank: #31. Votes: 21015. Organization: zai. License: MIT.

91.5% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,482 - 1,493

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 #43 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: multi_turn. Source rank: #47. Votes: 7297. Organization: zai. License: MIT.

88.8% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,467 - 1,483

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: overall. Source rank: #29. Votes: 45399. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,466 - 1,475

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 #20 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: creative_writing. Source rank: #21. Votes: 8979. Organization: zai. License: MIT.

94.9% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,457 - 1,471

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 #32 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: english. Source rank: #33. Votes: 18859. Organization: zai. License: MIT.

91.8% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,469 - 1,480

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: exclude_ties. Source rank: #29. Votes: 33697. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,470 - 1,481

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 #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts. Source rank: #39. Votes: 29821. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,475 - 1,485

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 #35 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts_english. Source rank: #36. Votes: 12565. Organization: zai. License: MIT.

90.9% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,473 - 1,486

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 #36 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: instruction_following. Source rank: #37. Votes: 15855. Organization: zai. License: MIT.

90.7% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,459 - 1,471

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 #27 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: longer_query. Source rank: #28. Votes: 21015. Organization: zai. License: MIT.

92.7% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,474 - 1,485

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 #34 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: multi_turn. Source rank: #36. Votes: 7297. Organization: zai. License: MIT.

91.2% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,461 - 1,476

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 #55 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.3%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

62.3%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 #46 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.2%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

76.2%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 #49 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.3%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

62.3%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 #55 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55.7%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

55.7%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #61 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.9%
Percentile: 7.7%
Last updated: stale
Eligibility: headline eligible

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

7.7% percentile inside its fair comparison set

62.9%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 #43 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.4%
Percentile: 35.4%
Last updated: stale
Eligibility: headline eligible

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

35.4% percentile inside its fair comparison set

68.4%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 #49 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

94%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 #34 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60.7%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

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

49.2% percentile inside its fair comparison set

60.7%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 #54 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

74%Raw benchmark value

Coding21 benchmarks72.3%

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 #7 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 50.8%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

98.5% percentile inside its fair comparison set

50.8%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 #76 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.2%
Percentile: 62.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

62.1% percentile inside its fair comparison set

51.2%Raw benchmark value

HiL-Bench

SL · Coding · Rubric

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

Rank #4 · Source label: GLM 5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 43.7%
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-hil-bench. Reported model configuration: GLM 5.2. Collapse policy: highest reported score per canonical model.

81.3% percentile inside its fair comparison set

43.7%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

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

Rank #51 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: coding. Source rank: #51. Votes: 12427. Organization: zai. License: MIT.

86.5% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,506 - 1,519

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 #45 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: coding. Source rank: #46. Votes: 12427. Organization: zai. License: MIT.

88.1% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,478 - 1,491

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #39 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64%
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

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

59.1% percentile inside its fair comparison set

64%Raw benchmark valueCI 54.6% - 73.4%

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 #25 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,605
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: overall. Source rank: #26. Votes: 14729. Organization: zai. License: MIT.

81.1% percentile inside its fair comparison set

1,605Raw benchmark valueCI 1,599 - 1,611

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 #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,562
Percentile: 76.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: webdev-html. Source rank: #31. Votes: 1730. Organization: zai. License: MIT.

76.8% percentile inside its fair comparison set

1,562Raw benchmark valueCI 1,546 - 1,577

Code Arena · Webdev React

AR · Coding · Human

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

Rank #25 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,618
Percentile: 78.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: webdev-react. Source rank: #26. Votes: 10272. Organization: zai. License: MIT.

78.8% percentile inside its fair comparison set

1,618Raw benchmark valueCI 1,611 - 1,626

Code Migration

VALS-AI · Coding · Objective

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

Rank #30 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 37.9%
Percentile: 57.4%
Last updated: recent
Eligibility: headline eligible

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

57.4% percentile inside its fair comparison set

37.9%Raw benchmark valueCI 29.7% - 46%

ProgramBench

VALS-AI · Coding · Objective

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

Rank #23 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.5%
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

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

72.4% percentile inside its fair comparison set

0.5%Raw benchmark valueCI 0% - 1.5%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

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

Rank #31 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.8%
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible

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

56.7% percentile inside its fair comparison set

67.8%Raw benchmark valueCI 65.8% - 69.7%

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #17 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.8%
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

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

80.5% percentile inside its fair comparison set

82.8%Raw benchmark valueCI 79.5% - 86.1%

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #88 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.5%
Percentile: 30.4%
Last updated: recent
Eligibility: headline eligible

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

30.4% percentile inside its fair comparison set

69.5%Raw benchmark valueCI 67.2% - 71.8%

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 #37 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.8%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

51.8%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 #24 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.7%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

79.7%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #31 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63.6%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

63.6%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 #39 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 36.7%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

36.7%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 #25 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% 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 #26 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.9%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

78.9%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 #16 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science17 benchmarks56.5%

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 #241 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9.8%
Percentile: 54.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

54.6% percentile inside its fair comparison set

9.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #238 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 68.6%
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

51.9% percentile inside its fair comparison set

68.6%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 #119 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.1%
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

74.2% percentile inside its fair comparison set

3.1%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 #27 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: math. Source rank: #28. Votes: 2035. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,475 - 1,501

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 #27 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: math. Source rank: #28. Votes: 2035. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,471 - 1,497

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

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

Rank #47 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.6%
Percentile: 63.7%
Last updated: recent
Eligibility: headline eligible

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

63.7% percentile inside its fair comparison set

85.6%Raw benchmark valueCI 82.1% - 89.1%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #39 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.7%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

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

69.6% percentile inside its fair comparison set

86.7%Raw benchmark valueCI 86.1% - 87.4%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #35 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89.8%
Percentile: 47.7%
Last updated: stale
Eligibility: headline eligible

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

47.7% percentile inside its fair comparison set

89.8%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 #53 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.6%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

78.6%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 #18 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

83.1% percentile inside its fair comparison set

98%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #37 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

76%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 #25 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

96.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #45 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

89%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 #49 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

75%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 #60 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.5%
Percentile: 9.2%
Last updated: stale
Eligibility: headline eligible

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

9.2% percentile inside its fair comparison set

65.5%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #56 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

94%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 #16 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80%Raw benchmark value

Professional reasoning32 benchmarks54.3%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #8 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.7%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

78.1% percentile inside its fair comparison set

33.7%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #40 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: expert. Source rank: #41. Votes: 4851. Organization: zai. License: MIT.

88.1% percentile inside its fair comparison set

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

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 #45 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #48. Votes: 8755. Organization: zai. License: MIT.

88.1% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,458 - 1,473

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 #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #39. Votes: 11229. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,439 - 1,453

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #25 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 93.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_legal_and_government. Source rank: #25. Votes: 3713. Organization: zai. License: MIT.

93.1% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,480 - 1,501

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 #24 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_life_and_physical_and_social_science. Source rank: #24. Votes: 7518. Organization: zai. License: MIT.

93.9% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,507

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #26 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_mathematical. Source rank: #27. Votes: 2480. Organization: zai. License: MIT.

93% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,482 - 1,506

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_medicine_and_healthcare. Source rank: #30. Votes: 3358. Organization: zai. License: MIT.

91.6% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,481 - 1,503

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 #42 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_software_and_it_services. Source rank: #42. Votes: 17871. Organization: zai. License: MIT.

89.1% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,500 - 1,512

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 #36 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_writing_and_literature_and_language. Source rank: #38. Votes: 12098. Organization: zai. License: MIT.

90.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,453 - 1,466

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #41 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: expert. Source rank: #42. Votes: 4851. Organization: zai. License: MIT.

87.8% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,477 - 1,495

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 #41 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #44. Votes: 8755. Organization: zai. License: MIT.

89.2% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,443 - 1,457

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 #26 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #27. Votes: 11229. Organization: zai. License: MIT.

93.3% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,443 - 1,456

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 #23 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 93.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_legal_and_government. Source rank: #24. Votes: 3713. Organization: zai. License: MIT.

93.7% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,475 - 1,495

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 #22 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_life_and_physical_and_social_science. Source rank: #23. Votes: 7518. Organization: zai. License: MIT.

94.4% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,482 - 1,497

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_mathematical. Source rank: #31. Votes: 2480. Organization: zai. License: MIT.

92.1% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,475 - 1,500

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_medicine_and_healthcare. Source rank: #29. Votes: 3358. Organization: zai. License: MIT.

92.2% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,464 - 1,486

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 #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_software_and_it_services. Source rank: #39. Votes: 17871. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,480 - 1,491

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_writing_and_literature_and_language. Source rank: #30. Votes: 12098. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,456 - 1,469

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #36 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31.3%
Percentile: 48.5%
Last updated: recent
Eligibility: headline eligible

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

48.5% percentile inside its fair comparison set

31.3%Raw benchmark valueCI 24.9% - 37.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #22 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 7.1%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

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

69.6% percentile inside its fair comparison set

7.1%Raw benchmark valueCI 3.2% - 11%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #40 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.1%
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

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

71.9% percentile inside its fair comparison set

84.1%Raw benchmark valueCI 83.2% - 85%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #37 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.7%
Percentile: 47.8%
Last updated: recent
Eligibility: headline eligible

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

47.8% percentile inside its fair comparison set

49.7%Raw benchmark valueCI 48% - 51.4%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #59 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 40.8%
Percentile: 38.9%
Last updated: recent
Eligibility: headline eligible

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

38.9% percentile inside its fair comparison set

40.8%Raw benchmark valueCI 36.5% - 45%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #44 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.5%
Percentile: 55.2%
Last updated: recent
Eligibility: headline eligible

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

55.2% percentile inside its fair comparison set

83.5%Raw benchmark valueCI 79.6% - 87.5%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #26 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 45.1%
Percentile: 24.2%
Last updated: recent
Eligibility: headline eligible

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

24.2% percentile inside its fair comparison set

45.1%Raw benchmark valueCI 36.5% - 53.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #49 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 73.3%
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

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

62.8% percentile inside its fair comparison set

73.3%Raw benchmark valueCI 71.6% - 75%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #41 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.7%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

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

38.5% percentile inside its fair comparison set

73.7%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #46 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

73.2%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #37 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.3%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

79.3%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #48 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.9%
Percentile: 27.7%
Last updated: stale
Eligibility: headline eligible

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

27.7% percentile inside its fair comparison set

45.9%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #55 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Search / tool use1 benchmark100%

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 #2 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 99.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

100% percentile inside its fair comparison set

99.1%Raw benchmark value

Long context2 benchmarks62.9%

Long Context Reasoning

AA · Long context · Objective

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

Rank #257 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 42.3%
Percentile: 43.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

43.7% percentile inside its fair comparison set

42.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

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

Rank #22 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.1%
Percentile: 82.1%
Last updated: aging
Eligibility: headline eligible

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

82.1% percentile inside its fair comparison set

66.1%Raw benchmark valueCI 64.3% - 67.9%

Multilingual18 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: chinese. Source rank: #30. Votes: 3261. Organization: zai. License: MIT.

91.8% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,510 - 1,531

Text Arena · French

AR · Multilingual · Human

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

Rank #35 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: french. Source rank: #38. Votes: 1599. Organization: zai. License: MIT.

86.8% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,474 - 1,507

Text Arena · German

AR · Multilingual · Human

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

Rank #32 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: german. Source rank: #35. Votes: 805. Organization: zai. License: MIT.

88.6% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,451 - 1,494

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 87.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: japanese. Source rank: #33. Votes: 702. Organization: zai. License: MIT.

87.7% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,431 - 1,480

Text Arena · Korean

AR · Multilingual · Human

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

Rank #20 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: korean. Source rank: #20. Votes: 879. Organization: zai. License: MIT.

92.2% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,429 - 1,471

Text Arena · Non English

AR · Multilingual · Human

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

Rank #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: non_english. Source rank: #39. Votes: 26529. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,457 - 1,467

Text Arena · Polish

AR · Multilingual · Human

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

Rank #49 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 75.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: polish. Source rank: #58. Votes: 738. Organization: zai. License: MIT.

75.9% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,432 - 1,476

Text Arena · Russian

AR · Multilingual · Human

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

Rank #38 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: russian. Source rank: #42. Votes: 5187. Organization: zai. License: MIT.

89.1% percentile inside its fair comparison set

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

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #18 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: spanish. Source rank: #18. Votes: 1314. Organization: zai. License: MIT.

93.4% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,460 - 1,494

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: chinese. Source rank: #31. Votes: 3261. Organization: zai. License: MIT.

92% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,509 - 1,531

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: french. Source rank: #30. Votes: 1599. Organization: zai. License: MIT.

89.1% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,462 - 1,494

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: german. Source rank: #32. Votes: 805. Organization: zai. License: MIT.

89.3% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,445 - 1,487

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #26 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: japanese. Source rank: #28. Votes: 702. Organization: zai. License: MIT.

89.7% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,426 - 1,475

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #22 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 91.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: korean. Source rank: #23. Votes: 879. Organization: zai. License: MIT.

91.4% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,427 - 1,468

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: non_english. Source rank: #31. Votes: 26529. Organization: zai. License: MIT.

92.6% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,454 - 1,464

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #38 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: polish. Source rank: #42. Votes: 738. Organization: zai. License: MIT.

81.4% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,431 - 1,475

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #33 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 90.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: russian. Source rank: #35. Votes: 5187. Organization: zai. License: MIT.

90.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,458 - 1,476

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #15 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 94.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: spanish. Source rank: #15. Votes: 1314. Organization: zai. License: MIT.

94.6% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,460 - 1,494

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

Model profile · Zhipu

glm-5.2-max

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

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

Visible coverage: 46.6%
Verified coverage: 46.6%
Spread: 92.3%
Last verified: Oct 3, 2026

69%capability fit

textcodedocument7 aliases35 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

Chat / text36 benchmarks67.6%

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 #144 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

74.2% percentile inside its fair comparison set

22Raw 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 #225 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 20.3%
Percentile: 50.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

50.6% percentile inside its fair comparison set

20.3%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 #48 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 66.3%
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

89.6% percentile inside its fair comparison set

66.3%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 #19 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 73.3%
Percentile: 94.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

94.8% percentile inside its fair comparison set

73.3%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #253 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.4 /1M input tokens
Percentile: 29.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

29.4% percentile inside its fair comparison set

$1.4 /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 #242 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $4.4 /1M output tokens
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

33.3% percentile inside its fair comparison set

$4.4 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

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

Rank #135 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 84.2 tokens/s
Percentile: 48.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.9% percentile inside its fair comparison set

84.2 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #146 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.10s
Percentile: 45.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

45.1% percentile inside its fair comparison set

3.10sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

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

Rank #164 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 26.85s
Percentile: 37.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

37.8% percentile inside its fair comparison set

26.85sRaw 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 #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: overall. Source rank: #32. Votes: 45399. Organization: zai. License: MIT.

92.3% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,471 - 1,480

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 #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: creative_writing. Source rank: #32. Votes: 8979. Organization: zai. License: MIT.

92% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,447 - 1,462

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 #32 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: english. Source rank: #33. Votes: 18859. Organization: zai. License: MIT.

91.8% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,477 - 1,488

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 #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: exclude_ties. Source rank: #33. Votes: 33697. Organization: zai. License: MIT.

92% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,480 - 1,491

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 #39 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 89.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts. Source rank: #40. Votes: 29821. Organization: zai. License: MIT.

89.9% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,491 - 1,501

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 #39 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts_english. Source rank: #40. Votes: 12565. Organization: zai. License: MIT.

89.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,491 - 1,503

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 #36 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: instruction_following. Source rank: #37. Votes: 15855. Organization: zai. License: MIT.

90.7% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,464 - 1,475

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 #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 91.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: longer_query. Source rank: #31. Votes: 21015. Organization: zai. License: MIT.

91.5% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,482 - 1,493

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 #43 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: multi_turn. Source rank: #47. Votes: 7297. Organization: zai. License: MIT.

88.8% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,467 - 1,483

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: overall. Source rank: #29. Votes: 45399. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,466 - 1,475

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 #20 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: creative_writing. Source rank: #21. Votes: 8979. Organization: zai. License: MIT.

94.9% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,457 - 1,471

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 #32 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: english. Source rank: #33. Votes: 18859. Organization: zai. License: MIT.

91.8% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,469 - 1,480

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: exclude_ties. Source rank: #29. Votes: 33697. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,470 - 1,481

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 #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts. Source rank: #39. Votes: 29821. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,475 - 1,485

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 #35 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: hard_prompts_english. Source rank: #36. Votes: 12565. Organization: zai. License: MIT.

90.9% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,473 - 1,486

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 #36 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: instruction_following. Source rank: #37. Votes: 15855. Organization: zai. License: MIT.

90.7% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,459 - 1,471

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 #27 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: longer_query. Source rank: #28. Votes: 21015. Organization: zai. License: MIT.

92.7% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,474 - 1,485

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 #34 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: multi_turn. Source rank: #36. Votes: 7297. Organization: zai. License: MIT.

91.2% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,461 - 1,476

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 #55 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.3%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

62.3%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 #46 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.2%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

76.2%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 #49 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.3%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

62.3%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 #55 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55.7%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

55.7%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #61 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.9%
Percentile: 7.7%
Last updated: stale
Eligibility: headline eligible

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

7.7% percentile inside its fair comparison set

62.9%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 #43 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.4%
Percentile: 35.4%
Last updated: stale
Eligibility: headline eligible

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

35.4% percentile inside its fair comparison set

68.4%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 #49 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

94%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 #34 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60.7%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

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

49.2% percentile inside its fair comparison set

60.7%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 #54 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

74%Raw benchmark value

Coding21 benchmarks72.3%

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 #7 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 50.8%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

98.5% percentile inside its fair comparison set

50.8%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 #76 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.2%
Percentile: 62.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

62.1% percentile inside its fair comparison set

51.2%Raw benchmark value

HiL-Bench

SL · Coding · Rubric

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

Rank #4 · Source label: GLM 5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 43.7%
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-hil-bench. Reported model configuration: GLM 5.2. Collapse policy: highest reported score per canonical model.

81.3% percentile inside its fair comparison set

43.7%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

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

Rank #51 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: coding. Source rank: #51. Votes: 12427. Organization: zai. License: MIT.

86.5% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,506 - 1,519

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 #45 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: coding. Source rank: #46. Votes: 12427. Organization: zai. License: MIT.

88.1% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,478 - 1,491

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #39 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64%
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

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

59.1% percentile inside its fair comparison set

64%Raw benchmark valueCI 54.6% - 73.4%

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 #25 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,605
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: overall. Source rank: #26. Votes: 14729. Organization: zai. License: MIT.

81.1% percentile inside its fair comparison set

1,605Raw benchmark valueCI 1,599 - 1,611

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 #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,562
Percentile: 76.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: webdev-html. Source rank: #31. Votes: 1730. Organization: zai. License: MIT.

76.8% percentile inside its fair comparison set

1,562Raw benchmark valueCI 1,546 - 1,577

Code Arena · Webdev React

AR · Coding · Human

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

Rank #25 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,618
Percentile: 78.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: webdev-react. Source rank: #26. Votes: 10272. Organization: zai. License: MIT.

78.8% percentile inside its fair comparison set

1,618Raw benchmark valueCI 1,611 - 1,626

Code Migration

VALS-AI · Coding · Objective

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

Rank #30 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 37.9%
Percentile: 57.4%
Last updated: recent
Eligibility: headline eligible

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

57.4% percentile inside its fair comparison set

37.9%Raw benchmark valueCI 29.7% - 46%

ProgramBench

VALS-AI · Coding · Objective

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

Rank #23 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.5%
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

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

72.4% percentile inside its fair comparison set

0.5%Raw benchmark valueCI 0% - 1.5%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

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

Rank #31 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.8%
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible

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

56.7% percentile inside its fair comparison set

67.8%Raw benchmark valueCI 65.8% - 69.7%

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #17 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.8%
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

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

80.5% percentile inside its fair comparison set

82.8%Raw benchmark valueCI 79.5% - 86.1%

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #88 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.5%
Percentile: 30.4%
Last updated: recent
Eligibility: headline eligible

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

30.4% percentile inside its fair comparison set

69.5%Raw benchmark valueCI 67.2% - 71.8%

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 #37 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.8%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

51.8%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 #24 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.7%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

79.7%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #31 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63.6%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

63.6%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 #39 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 36.7%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

36.7%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 #25 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% 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 #26 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.9%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

78.9%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 #16 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science17 benchmarks56.5%

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 #241 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9.8%
Percentile: 54.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

54.6% percentile inside its fair comparison set

9.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #238 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 68.6%
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

51.9% percentile inside its fair comparison set

68.6%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 #119 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.1%
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

74.2% percentile inside its fair comparison set

3.1%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 #27 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: math. Source rank: #28. Votes: 2035. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,475 - 1,501

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 #27 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: math. Source rank: #28. Votes: 2035. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,471 - 1,497

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

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

Rank #47 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.6%
Percentile: 63.7%
Last updated: recent
Eligibility: headline eligible

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

63.7% percentile inside its fair comparison set

85.6%Raw benchmark valueCI 82.1% - 89.1%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #39 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.7%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

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

69.6% percentile inside its fair comparison set

86.7%Raw benchmark valueCI 86.1% - 87.4%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #35 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89.8%
Percentile: 47.7%
Last updated: stale
Eligibility: headline eligible

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

47.7% percentile inside its fair comparison set

89.8%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 #53 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.6%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

78.6%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 #18 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

83.1% percentile inside its fair comparison set

98%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #37 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

76%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 #25 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

96.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #45 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

89%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 #49 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

75%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 #60 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.5%
Percentile: 9.2%
Last updated: stale
Eligibility: headline eligible

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

9.2% percentile inside its fair comparison set

65.5%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #56 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

94%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 #16 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80%Raw benchmark value

Professional reasoning32 benchmarks54.3%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #8 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.7%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

78.1% percentile inside its fair comparison set

33.7%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #40 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: expert. Source rank: #41. Votes: 4851. Organization: zai. License: MIT.

88.1% percentile inside its fair comparison set

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

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 #45 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #48. Votes: 8755. Organization: zai. License: MIT.

88.1% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,458 - 1,473

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 #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #39. Votes: 11229. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,439 - 1,453

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #25 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 93.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_legal_and_government. Source rank: #25. Votes: 3713. Organization: zai. License: MIT.

93.1% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,480 - 1,501

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 #24 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_life_and_physical_and_social_science. Source rank: #24. Votes: 7518. Organization: zai. License: MIT.

93.9% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,507

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #26 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_mathematical. Source rank: #27. Votes: 2480. Organization: zai. License: MIT.

93% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,482 - 1,506

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_medicine_and_healthcare. Source rank: #30. Votes: 3358. Organization: zai. License: MIT.

91.6% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,481 - 1,503

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 #42 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_software_and_it_services. Source rank: #42. Votes: 17871. Organization: zai. License: MIT.

89.1% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,500 - 1,512

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 #36 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_writing_and_literature_and_language. Source rank: #38. Votes: 12098. Organization: zai. License: MIT.

90.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,453 - 1,466

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #41 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: expert. Source rank: #42. Votes: 4851. Organization: zai. License: MIT.

87.8% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,477 - 1,495

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 #41 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #44. Votes: 8755. Organization: zai. License: MIT.

89.2% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,443 - 1,457

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 #26 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #27. Votes: 11229. Organization: zai. License: MIT.

93.3% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,443 - 1,456

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 #23 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 93.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_legal_and_government. Source rank: #24. Votes: 3713. Organization: zai. License: MIT.

93.7% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,475 - 1,495

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 #22 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_life_and_physical_and_social_science. Source rank: #23. Votes: 7518. Organization: zai. License: MIT.

94.4% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,482 - 1,497

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_mathematical. Source rank: #31. Votes: 2480. Organization: zai. License: MIT.

92.1% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,475 - 1,500

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_medicine_and_healthcare. Source rank: #29. Votes: 3358. Organization: zai. License: MIT.

92.2% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,464 - 1,486

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 #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_software_and_it_services. Source rank: #39. Votes: 17871. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,480 - 1,491

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 #28 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: industry_writing_and_literature_and_language. Source rank: #30. Votes: 12098. Organization: zai. License: MIT.

92.8% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,456 - 1,469

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #36 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31.3%
Percentile: 48.5%
Last updated: recent
Eligibility: headline eligible

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

48.5% percentile inside its fair comparison set

31.3%Raw benchmark valueCI 24.9% - 37.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #22 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 7.1%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

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

69.6% percentile inside its fair comparison set

7.1%Raw benchmark valueCI 3.2% - 11%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #40 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.1%
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

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

71.9% percentile inside its fair comparison set

84.1%Raw benchmark valueCI 83.2% - 85%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #37 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.7%
Percentile: 47.8%
Last updated: recent
Eligibility: headline eligible

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

47.8% percentile inside its fair comparison set

49.7%Raw benchmark valueCI 48% - 51.4%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #59 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 40.8%
Percentile: 38.9%
Last updated: recent
Eligibility: headline eligible

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

38.9% percentile inside its fair comparison set

40.8%Raw benchmark valueCI 36.5% - 45%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #44 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.5%
Percentile: 55.2%
Last updated: recent
Eligibility: headline eligible

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

55.2% percentile inside its fair comparison set

83.5%Raw benchmark valueCI 79.6% - 87.5%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #26 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 45.1%
Percentile: 24.2%
Last updated: recent
Eligibility: headline eligible

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

24.2% percentile inside its fair comparison set

45.1%Raw benchmark valueCI 36.5% - 53.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #49 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 73.3%
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

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

62.8% percentile inside its fair comparison set

73.3%Raw benchmark valueCI 71.6% - 75%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #41 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.7%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

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

38.5% percentile inside its fair comparison set

73.7%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #46 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

73.2%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #37 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.3%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

79.3%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #48 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.9%
Percentile: 27.7%
Last updated: stale
Eligibility: headline eligible

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

27.7% percentile inside its fair comparison set

45.9%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #55 · Source label: glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Search / tool use1 benchmark100%

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 #2 · Source label: GLM-5.2 (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 99.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

100% percentile inside its fair comparison set

99.1%Raw benchmark value

Long context2 benchmarks62.9%

Long Context Reasoning

AA · Long context · Objective

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

Rank #257 · Source label: GLM-5.2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 42.3%
Percentile: 43.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

43.7% percentile inside its fair comparison set

42.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

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

Rank #22 · Source label: zai/glm-5.2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.1%
Percentile: 82.1%
Last updated: aging
Eligibility: headline eligible

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

82.1% percentile inside its fair comparison set

66.1%Raw benchmark valueCI 64.3% - 67.9%

Multilingual18 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: chinese. Source rank: #30. Votes: 3261. Organization: zai. License: MIT.

91.8% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,510 - 1,531

Text Arena · French

AR · Multilingual · Human

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

Rank #35 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: french. Source rank: #38. Votes: 1599. Organization: zai. License: MIT.

86.8% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,474 - 1,507

Text Arena · German

AR · Multilingual · Human

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

Rank #32 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: german. Source rank: #35. Votes: 805. Organization: zai. License: MIT.

88.6% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,451 - 1,494

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #31 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 87.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: japanese. Source rank: #33. Votes: 702. Organization: zai. License: MIT.

87.7% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,431 - 1,480

Text Arena · Korean

AR · Multilingual · Human

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

Rank #20 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: korean. Source rank: #20. Votes: 879. Organization: zai. License: MIT.

92.2% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,429 - 1,471

Text Arena · Non English

AR · Multilingual · Human

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

Rank #37 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: non_english. Source rank: #39. Votes: 26529. Organization: zai. License: MIT.

90.4% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,457 - 1,467

Text Arena · Polish

AR · Multilingual · Human

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

Rank #49 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 75.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: polish. Source rank: #58. Votes: 738. Organization: zai. License: MIT.

75.9% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,432 - 1,476

Text Arena · Russian

AR · Multilingual · Human

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

Rank #38 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: russian. Source rank: #42. Votes: 5187. Organization: zai. License: MIT.

89.1% percentile inside its fair comparison set

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

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #18 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: spanish. Source rank: #18. Votes: 1314. Organization: zai. License: MIT.

93.4% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,460 - 1,494

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: chinese. Source rank: #31. Votes: 3261. Organization: zai. License: MIT.

92% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,509 - 1,531

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: french. Source rank: #30. Votes: 1599. Organization: zai. License: MIT.

89.1% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,462 - 1,494

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #30 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: german. Source rank: #32. Votes: 805. Organization: zai. License: MIT.

89.3% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,445 - 1,487

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #26 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: japanese. Source rank: #28. Votes: 702. Organization: zai. License: MIT.

89.7% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,426 - 1,475

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #22 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 91.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: korean. Source rank: #23. Votes: 879. Organization: zai. License: MIT.

91.4% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,427 - 1,468

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: non_english. Source rank: #31. Votes: 26529. Organization: zai. License: MIT.

92.6% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,454 - 1,464

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #38 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: polish. Source rank: #42. Votes: 738. Organization: zai. License: MIT.

81.4% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,431 - 1,475

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #33 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 90.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: russian. Source rank: #35. Votes: 5187. Organization: zai. License: MIT.

90.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,458 - 1,476

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #15 · Source label: glm-5.2-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 94.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `glm-5.2-max`. Category: spanish. Source rank: #15. Votes: 1314. Organization: zai. License: MIT.

94.6% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,460 - 1,494

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

glm-5.2-max

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

glm-5.2-max

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks