Model profile · Zhipu

glm-5v-turbo

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 30.8%
Verified coverage: 30.8%
Spread: n/a
Last verified: Jun 20, 2026

visiontextcodedocument2 aliases11 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text13 benchmarks43.7%

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 #33 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 34
Percentile: 91.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

91.9% percentile inside its fair comparison set

34Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

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

Rank #32 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29.1%
Percentile: 89.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

89.6% percentile inside its fair comparison set

29.1%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 #65 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.1%
Percentile: 78.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

78.5% percentile inside its fair comparison set

32.1%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #56 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.1%
Percentile: 82.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

82.5% percentile inside its fair comparison set

61.1%Raw benchmark value

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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 27.2%
Percentile: 23.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

23.1% percentile inside its fair comparison set

27.2%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 #83

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.3%
Percentile: 25%
Last updated: archived
Eligibility: benchmark_derived_model

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

25% percentile inside its fair comparison set

62.3%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #83

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 22.8%
Percentile: 25%
Last updated: archived
Eligibility: benchmark_derived_model

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

25% percentile inside its fair comparison set

22.8%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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25.9%
Percentile: 23.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

23.1% percentile inside its fair comparison set

25.9%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #85

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 28.4%
Percentile: 22.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

22.2% percentile inside its fair comparison set

28.4%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #83

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 31.7%
Percentile: 24.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

24.1% percentile inside its fair comparison set

31.7%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #69

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86%
Percentile: 39.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

39.8% percentile inside its fair comparison set

86%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 #70

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 46.8%
Percentile: 36.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

36.1% percentile inside its fair comparison set

46.8%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 #100

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54%
Percentile: 7.5%
Last updated: archived
Eligibility: benchmark_derived_model

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

7.5% percentile inside its fair comparison set

54%Raw benchmark value

Coding9 benchmarks40.9%

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 #53 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.6%
Percentile: 83.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

83.4% percentile inside its fair comparison set

32.6%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 #30 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.5%
Percentile: 92.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

92.1% percentile inside its fair comparison set

43.5%Raw benchmark value

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 #105

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 3.3%
Percentile: 5.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

5.6% percentile inside its fair comparison set

3.3%Raw benchmark value

Coding

LB · Coding · Objective

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

Rank #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.9%
Percentile: 51.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

51.9% percentile inside its fair comparison set

73.9%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 #106

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 0%
Percentile: 5.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

5.6% percentile inside its fair comparison set

0%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 #104

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 0%
Percentile: 9.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

9.3% percentile inside its fair comparison set

0%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 #103

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 8.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

8.3% percentile inside its fair comparison set

10%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 #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 61.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

61.1% percentile inside its fair comparison set

76.1%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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

50.9% percentile inside its fair comparison set

71.7%Raw benchmark value

Reasoning / math / science13 benchmarks52.6%

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 #53 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.8%
Percentile: 85.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `hle`.

85.9% percentile inside its fair comparison set

15.8%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 #62 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.9%
Percentile: 84%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

84% percentile inside its fair comparison set

80.9%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 #67 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.6%
Percentile: 80.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

80.1% percentile inside its fair comparison set

0.6%Raw benchmark value

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #70

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.4%
Percentile: 36.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

36.1% percentile inside its fair comparison set

70.4%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #73

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 56.1%
Percentile: 33.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

33.3% percentile inside its fair comparison set

56.1%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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98.8%
Percentile: 95.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

95.4% percentile inside its fair comparison set

98.8%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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

24.1% percentile inside its fair comparison set

13%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

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

Rank #77

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.3%
Percentile: 31.5%
Last updated: archived
Eligibility: benchmark_derived_model

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

31.5% percentile inside its fair comparison set

85.3%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 #53

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.5%
Percentile: 51.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

51.9% percentile inside its fair comparison set

84.5%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 #76

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.9%
Percentile: 33.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

33.3% percentile inside its fair comparison set

51.9%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 #79

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18.5%
Percentile: 27.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

27.1% percentile inside its fair comparison set

18.5%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 #46

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 60.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

60.2% 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 #68

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60%
Percentile: 40.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

40.7% percentile inside its fair comparison set

60%Raw benchmark value

Professional reasoning5 benchmarks49.8%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54.1%
Percentile: 48.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

48.1% percentile inside its fair comparison set

54.1%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 49.6%
Percentile: 23.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

23.1% percentile inside its fair comparison set

49.6%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.9%
Percentile: 48.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

48.1% percentile inside its fair comparison set

20.9%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #49

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 43.5%
Percentile: 55.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

55.6% percentile inside its fair comparison set

43.5%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

74.1% percentile inside its fair comparison set

98%Raw benchmark value

Search / tool use1 benchmark99.4%

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 #5 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 98.5%
Percentile: 99.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

99.4% percentile inside its fair comparison set

98.5%Raw benchmark value

Long context1 benchmark86.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #44 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61%
Percentile: 86.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

86.7% percentile inside its fair comparison set

61%Raw benchmark value

Vision understanding15 benchmarks69.9%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #21 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 72.8%
Percentile: 85.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

85.2% percentile inside its fair comparison set

72.8%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #31

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 72.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #40. Votes: 16521. Organization: zai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,225 - 1,240

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #32

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,226
Percentile: 43.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: creative_writing_vision. Source rank: #40. Votes: 878. Organization: zai. License: Proprietary.

43.6% percentile inside its fair comparison set

1,226Raw benchmark valueCI 1,205 - 1,247

Vision Arena · Diagram

AR · Vision understanding · Human

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

Rank #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 62.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: diagram. Source rank: #36. Votes: 4466. Organization: zai. License: Proprietary.

62.9% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,251 - 1,272

Vision Arena · English

AR · Vision understanding · Human

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

Rank #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,239
Percentile: 76.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: english. Source rank: #35. Votes: 7328. Organization: zai. License: Proprietary.

76.1% percentile inside its fair comparison set

1,239Raw benchmark valueCI 1,229 - 1,249

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #32

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,258
Percentile: 54.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: homework. Source rank: #41. Votes: 2451. Organization: zai. License: Proprietary.

54.4% percentile inside its fair comparison set

1,258Raw benchmark valueCI 1,245 - 1,271

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 65.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: humor. Source rank: #23. Votes: 554. Organization: zai. License: Proprietary.

65.3% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,218 - 1,271

Vision Arena · Ocr

AR · Vision understanding · Human

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

Rank #32

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 55.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: ocr. Source rank: #41. Votes: 11854. Organization: zai. License: Proprietary.

55.7% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,238 - 1,252

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,266
Percentile: 84.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #23. Votes: 16521. Organization: zai. License: Proprietary.

84.4% percentile inside its fair comparison set

1,266Raw benchmark valueCI 1,258 - 1,273

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #19

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,263
Percentile: 67.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: creative_writing_vision. Source rank: #24. Votes: 878. Organization: zai. License: Proprietary.

67.3% percentile inside its fair comparison set

1,263Raw benchmark valueCI 1,243 - 1,284

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

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

Rank #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 75.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: diagram. Source rank: #23. Votes: 4466. Organization: zai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,270 - 1,291

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,274
Percentile: 86.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: english. Source rank: #20. Votes: 7328. Organization: zai. License: Proprietary.

86.2% percentile inside its fair comparison set

1,274Raw benchmark valueCI 1,264 - 1,284

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

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

Rank #26

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,277
Percentile: 63.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: homework. Source rank: #33. Votes: 2451. Organization: zai. License: Proprietary.

63.2% percentile inside its fair comparison set

1,277Raw benchmark valueCI 1,264 - 1,290

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,285
Percentile: 83.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: humor. Source rank: #12. Votes: 554. Organization: zai. License: Proprietary.

83.7% percentile inside its fair comparison set

1,285Raw benchmark valueCI 1,259 - 1,311

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #20

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,270
Percentile: 72.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: ocr. Source rank: #25. Votes: 11854. Organization: zai. License: Proprietary.

72.9% percentile inside its fair comparison set

1,270Raw benchmark valueCI 1,263 - 1,277

Document understanding2 benchmarks10.4%

Document Arena

AR · Document understanding · Human

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

Rank #25

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 0%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #29. Votes: 1389. Organization: zai. License: Proprietary.

0% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,383 - 1,414

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #20

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 20.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #23. Votes: 1389. Organization: zai. License: Proprietary.

20.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,398 - 1,429

Multilingual2 benchmarks84.4%

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,301
Percentile: 80.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: chinese. Source rank: #21. Votes: 978. Organization: zai. License: Proprietary.

80.5% percentile inside its fair comparison set

1,301Raw benchmark valueCI 1,277 - 1,325

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 88.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: chinese. Source rank: #14. Votes: 978. Organization: zai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,319 - 1,366

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

Model profile · Zhipu

glm-5v-turbo

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 30.8%
Verified coverage: 30.8%
Spread: n/a
Last verified: Jun 20, 2026

visiontextcodedocument2 aliases11 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text13 benchmarks43.7%

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 #33 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 34
Percentile: 91.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

91.9% percentile inside its fair comparison set

34Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

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

Rank #32 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29.1%
Percentile: 89.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

89.6% percentile inside its fair comparison set

29.1%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 #65 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.1%
Percentile: 78.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

78.5% percentile inside its fair comparison set

32.1%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #56 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.1%
Percentile: 82.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

82.5% percentile inside its fair comparison set

61.1%Raw benchmark value

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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 27.2%
Percentile: 23.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

23.1% percentile inside its fair comparison set

27.2%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 #83

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.3%
Percentile: 25%
Last updated: archived
Eligibility: benchmark_derived_model

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

25% percentile inside its fair comparison set

62.3%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #83

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 22.8%
Percentile: 25%
Last updated: archived
Eligibility: benchmark_derived_model

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

25% percentile inside its fair comparison set

22.8%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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25.9%
Percentile: 23.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

23.1% percentile inside its fair comparison set

25.9%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #85

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 28.4%
Percentile: 22.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

22.2% percentile inside its fair comparison set

28.4%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #83

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 31.7%
Percentile: 24.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

24.1% percentile inside its fair comparison set

31.7%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #69

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86%
Percentile: 39.8%
Last updated: archived
Eligibility: benchmark_derived_model

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

39.8% percentile inside its fair comparison set

86%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 #70

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 46.8%
Percentile: 36.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

36.1% percentile inside its fair comparison set

46.8%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 #100

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54%
Percentile: 7.5%
Last updated: archived
Eligibility: benchmark_derived_model

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

7.5% percentile inside its fair comparison set

54%Raw benchmark value

Coding9 benchmarks40.9%

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 #53 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.6%
Percentile: 83.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

83.4% percentile inside its fair comparison set

32.6%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 #30 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.5%
Percentile: 92.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

92.1% percentile inside its fair comparison set

43.5%Raw benchmark value

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 #105

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 3.3%
Percentile: 5.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

5.6% percentile inside its fair comparison set

3.3%Raw benchmark value

Coding

LB · Coding · Objective

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

Rank #54

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.9%
Percentile: 51.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

51.9% percentile inside its fair comparison set

73.9%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 #106

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 0%
Percentile: 5.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

5.6% percentile inside its fair comparison set

0%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 #104

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 0%
Percentile: 9.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

9.3% percentile inside its fair comparison set

0%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 #103

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 8.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

8.3% percentile inside its fair comparison set

10%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 #48

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 61.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

61.1% percentile inside its fair comparison set

76.1%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 #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

50.9% percentile inside its fair comparison set

71.7%Raw benchmark value

Reasoning / math / science13 benchmarks52.6%

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 #53 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.8%
Percentile: 85.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `hle`.

85.9% percentile inside its fair comparison set

15.8%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 #62 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.9%
Percentile: 84%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

84% percentile inside its fair comparison set

80.9%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 #67 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.6%
Percentile: 80.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

80.1% percentile inside its fair comparison set

0.6%Raw benchmark value

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #70

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.4%
Percentile: 36.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

36.1% percentile inside its fair comparison set

70.4%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #73

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 56.1%
Percentile: 33.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

33.3% percentile inside its fair comparison set

56.1%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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98.8%
Percentile: 95.4%
Last updated: archived
Eligibility: benchmark_derived_model

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

95.4% percentile inside its fair comparison set

98.8%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 #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

24.1% percentile inside its fair comparison set

13%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

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

Rank #77

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.3%
Percentile: 31.5%
Last updated: archived
Eligibility: benchmark_derived_model

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

31.5% percentile inside its fair comparison set

85.3%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 #53

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.5%
Percentile: 51.9%
Last updated: archived
Eligibility: benchmark_derived_model

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

51.9% percentile inside its fair comparison set

84.5%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 #76

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.9%
Percentile: 33.3%
Last updated: archived
Eligibility: benchmark_derived_model

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

33.3% percentile inside its fair comparison set

51.9%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 #79

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18.5%
Percentile: 27.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

27.1% percentile inside its fair comparison set

18.5%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 #46

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 60.2%
Last updated: archived
Eligibility: benchmark_derived_model

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

60.2% 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 #68

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60%
Percentile: 40.7%
Last updated: archived
Eligibility: benchmark_derived_model

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

40.7% percentile inside its fair comparison set

60%Raw benchmark value

Professional reasoning5 benchmarks49.8%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54.1%
Percentile: 48.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

48.1% percentile inside its fair comparison set

54.1%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #84

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 49.6%
Percentile: 23.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

23.1% percentile inside its fair comparison set

49.6%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #57

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.9%
Percentile: 48.1%
Last updated: archived
Eligibility: benchmark_derived_model

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

48.1% percentile inside its fair comparison set

20.9%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #49

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 43.5%
Percentile: 55.6%
Last updated: archived
Eligibility: benchmark_derived_model

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

55.6% percentile inside its fair comparison set

43.5%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #64

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

74.1% percentile inside its fair comparison set

98%Raw benchmark value

Search / tool use1 benchmark99.4%

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 #5 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 98.5%
Percentile: 99.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

99.4% percentile inside its fair comparison set

98.5%Raw benchmark value

Long context1 benchmark86.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #44 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61%
Percentile: 86.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

86.7% percentile inside its fair comparison set

61%Raw benchmark value

Vision understanding15 benchmarks69.9%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #21 · Source label: GLM 5V Turbo (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 72.8%
Percentile: 85.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

85.2% percentile inside its fair comparison set

72.8%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #31

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 72.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #40. Votes: 16521. Organization: zai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,225 - 1,240

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #32

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,226
Percentile: 43.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: creative_writing_vision. Source rank: #40. Votes: 878. Organization: zai. License: Proprietary.

43.6% percentile inside its fair comparison set

1,226Raw benchmark valueCI 1,205 - 1,247

Vision Arena · Diagram

AR · Vision understanding · Human

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

Rank #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 62.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: diagram. Source rank: #36. Votes: 4466. Organization: zai. License: Proprietary.

62.9% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,251 - 1,272

Vision Arena · English

AR · Vision understanding · Human

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

Rank #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,239
Percentile: 76.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: english. Source rank: #35. Votes: 7328. Organization: zai. License: Proprietary.

76.1% percentile inside its fair comparison set

1,239Raw benchmark valueCI 1,229 - 1,249

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #32

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,258
Percentile: 54.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: homework. Source rank: #41. Votes: 2451. Organization: zai. License: Proprietary.

54.4% percentile inside its fair comparison set

1,258Raw benchmark valueCI 1,245 - 1,271

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 65.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: humor. Source rank: #23. Votes: 554. Organization: zai. License: Proprietary.

65.3% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,218 - 1,271

Vision Arena · Ocr

AR · Vision understanding · Human

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

Rank #32

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 55.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: ocr. Source rank: #41. Votes: 11854. Organization: zai. License: Proprietary.

55.7% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,238 - 1,252

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,266
Percentile: 84.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #23. Votes: 16521. Organization: zai. License: Proprietary.

84.4% percentile inside its fair comparison set

1,266Raw benchmark valueCI 1,258 - 1,273

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #19

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,263
Percentile: 67.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: creative_writing_vision. Source rank: #24. Votes: 878. Organization: zai. License: Proprietary.

67.3% percentile inside its fair comparison set

1,263Raw benchmark valueCI 1,243 - 1,284

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

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

Rank #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 75.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: diagram. Source rank: #23. Votes: 4466. Organization: zai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,270 - 1,291

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,274
Percentile: 86.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: english. Source rank: #20. Votes: 7328. Organization: zai. License: Proprietary.

86.2% percentile inside its fair comparison set

1,274Raw benchmark valueCI 1,264 - 1,284

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

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

Rank #26

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,277
Percentile: 63.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: homework. Source rank: #33. Votes: 2451. Organization: zai. License: Proprietary.

63.2% percentile inside its fair comparison set

1,277Raw benchmark valueCI 1,264 - 1,290

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,285
Percentile: 83.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: humor. Source rank: #12. Votes: 554. Organization: zai. License: Proprietary.

83.7% percentile inside its fair comparison set

1,285Raw benchmark valueCI 1,259 - 1,311

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #20

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,270
Percentile: 72.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: ocr. Source rank: #25. Votes: 11854. Organization: zai. License: Proprietary.

72.9% percentile inside its fair comparison set

1,270Raw benchmark valueCI 1,263 - 1,277

Document understanding2 benchmarks10.4%

Document Arena

AR · Document understanding · Human

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

Rank #25

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 0%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #29. Votes: 1389. Organization: zai. License: Proprietary.

0% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,383 - 1,414

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #20

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 20.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: overall. Source rank: #23. Votes: 1389. Organization: zai. License: Proprietary.

20.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,398 - 1,429

Multilingual2 benchmarks84.4%

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,301
Percentile: 80.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: chinese. Source rank: #21. Votes: 978. Organization: zai. License: Proprietary.

80.5% percentile inside its fair comparison set

1,301Raw benchmark valueCI 1,277 - 1,325

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 88.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `glm-5v-turbo`. Category: chinese. Source rank: #14. Votes: 978. Organization: zai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,319 - 1,366

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

glm-5v-turbo

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

glm-5v-turbo

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks