priorsBuilder

Zhipu · released 2026-08-26

GLM 5.3 Flash

Measured on 75 benchmarks.

General frontier

40.8

#26 of 32 models · best at max

Your mix’s benchmarks

5 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #83max of 58739.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #96max of 5267.5

Leader: Opus 5.5 · 46.4

coding

DeepSWE v1.1

70 results
  1. #30max of 7063.4%

Leader: GPT-6 Astra · 74.1%

math

FrontierMath Tier 4 (v2)

70 results
  1. #51max of 7017.1%

Leader: GPT-6.1 Sol · 100.0%

agentic

Terminal-Bench 4.0

35 results
  1. #23none of 3535.8%

Leader: Opus 5.5 · 64.8%

All 75 benchmarks

show 70 more

agentic

AA-Briefcase v1.1

224 results
  1. #45max of 2241454

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #34max of 50-1.0%

Leader: Opus 5.5 · 15.5%

agentic

AutomationBench-AA

219 results
  1. #31max of 21960.4%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #38max of 5033.2%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #31max of 796.7%

Leader: Muse Spark 1.2 · 25.4%

agentic

ITBench-AA

45 results
  1. #4max of 4551.2%

Leader: GPT-5.6 Sol · 56.2%

agentic

Legal Research Bench

78 results
  1. #17max of 7845.2%

Leader: Muse Spark 1.3 · 55.3%

agentic

SkillsBench

34 results
  1. #29max of 3440.2%

Leader: DeepSeek V4.1 Flash · 69.8%

agentic

Tax Agent Bench

69 results
  1. #21max of 6931.6%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench Science (Vals)

40 results
  1. #33max of 402.9%

Leader: GPT-6 Astra · 62.9%

agentic

τ³-Banking

206 results
  1. #10max of 20647.2%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #19max of 581581

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #25max of 1221609

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #51max of 7720.5%

Leader: Sonnet 5.5 · 69.8%

coding

FrontierCode 1.1 Extended

130 results
  1. #97max of 13046.2%

Leader: Opus 5.5 · 65.3%

coding

FrontierCode 1.1 Main

130 results
  1. #97max of 13031.8%

Leader: Opus 5.5 · 54.6%

coding

FrontierSWE v2

21 results
  1. #17max of 2118.1%

Leader: GPT-6 Astra · 65.5%

coding

IOI

44 results
  1. #23max of 4452.5%

Leader: Gemini 4 · 100.0%

coding

LiveCodeBench (Vals)

127 results
  1. #69max of 12780.5%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #35max of 627.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #62max of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #43max of 6248.6%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #89max of 22651.6%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #10max of 8592.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #37max of 7462.9%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Science-AA

46 results
  1. #35max of 464.8%

Leader: GPT-6 Astra · 63.3%

coding

Terminal-Bench v2.1-AA

238 results
  1. #32max of 23884.3%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #41max of 21632.8%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench 1-100

22 results
  1. #14max of 2216.0%

Leader: Opus 5.5 · 30.4%

coding

Vibe Code Bench v1.1

105 results
  1. #65max of 10530.8%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #53max of 61041.8

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #37max of 2201475

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #50max of 2201472

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #68max of 177$0.28

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #51max of 177$306

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #16max of 721821

Leader: GPT-6 Astra Pro · 2281

creative

VoxelBench (text)

55 results
  1. #22max of 551748

Leader: GPT-6 Astra · 2732

economics

Excel Modeling Benchmark

74 results
  1. #47max of 7455.9%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #13max of 7857.9%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #91max of 21015.4%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #19max of 2881644

Leader: Opus 5.5 · 1866

economics

TaxEval (Vals)

125 results
  1. #16max of 12575.6%

Leader: Muse Spark 1.2 · 80.4%

knowledge

AA-Omniscience Accuracy

526 results
  1. #199max of 52627.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #33max of 52672.4%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

GPQA Diamond

539 results
  1. #49max of 53991.2%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #43max of 12286.4%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

Harvey LAB-AA v1.1

27 results
  1. #18max of 270.8%

Leader: Muse Wonder Full (Max) · 13.1%

knowledge

MedScribe

96 results
  1. #8max of 9688.9%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #48max of 12286.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #23max of 8186.0%

Leader: Fable 5.1 · 90.6%

long-context

AA-LCR v1.1

523 results
  1. #79max of 52380.0%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #12max of 9451.1%

Leader: Sonnet 5.5 · 75.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #42max of 11555.8%

Leader: GPT-6.1 Sol · 93.7%

math

ProofBench v1.1

52 results
  1. #42max of 5221.0%

Leader: Sonnet 5.5 · 100.0%

other

Arena Vision

116 results
  1. #34max of 1161273

Leader: Fable 5 · 1308

reasoning

ARC-AGI-1

215 results
  1. #63max of 21591.0%
  2. #122high of 21571.8%
  3. #157low of 21547.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #64max of 21665.8%
  2. #97high of 21650.1%
  3. #119low of 21627.9%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #85max of 52915.4%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Humanity's Sixth Sense

25 results
  1. #16max of 2526.8%

Leader: GPT-6 Astra · 53.6%

reasoning

LegalBench

135 results
  1. #44max of 13583.9%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #64high of 10259.6%
  2. #79low of 10251.0%

Leader: GPT-6 Astra · 91.2%

reliability

Tool-call error rate

171 results
  1. #94max of 1711.5%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #157max of 18197.4%

Leader: GPT-5 Pro · 100.0%

safety

CWE-Bench

19 results
  1. #10max of 1955.8%

Leader: Grok 4.7 · 68.3%

safety

CyberBench v1.1

45 results
  1. #27max of 4567.9%

Leader: Wonder · 80.4%

safety

SRE Bench

32 results
  1. #26max of 320.8%

Leader: GPT-6 Astra · 56.9%

speed

Latency (Time to First Token)

351 results
  1. #198max of 3512.9s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #242max of 35166.7

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #64max of 1771.0s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #81max of 17668.5

Leader: Muse Spark 1.1 · 204.3