The LLM benchmark aggregator.

GLM-5.3 Flash

Z.ai · 321B · open weights

Strongest in Knowledge work (#13 of 178), weakest in Jailbreak resistance (#233 of 272). Above par in 20 of 28 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of Gemini 3.5 Flash and GLM-5.2.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Agents63.1−5#15/2682/5

Knowledge work67.1−6.5#13/1782/2

Professional57−4.6#18/1681/1

Finance58.3−4.6#15/1511/1

Medical57.9−8.9#20/1401/1

Legal57−10.1#28/1511/1

Human preference64.1−3.4#32/3421/1

Coding52.7−16.4#52/1652/5

Code generation53.3−16.7#33/771/2

Agentic coding52.6−16.1#56/1572/4

Knowledge55−8.5#52/1381/2

Academic knowledge56−7.9#48/1231/1

Core abilities46.9−20.5#129/2042/3

Data analysis55−11.1#26/571/1

Language46.3−25.2#36/571/1

Instruction following26−47.7#57/571/1

General intelligence53.7−16.4#69/2042/3

Reasoning42.6−24.3#141/1782/4

Science57.2−6.3#43/1221/1

Reasoning41.4−27.7#107/1401/3

Mathematics36.8−28.9#120/1402/2

Safety50.3−11.2#175/3371/3

Fairness66.3−3.7#18/3001/2

Toxicity avoidance55.6−3.4#93/2721/1

Secure code51.2−15.3#148/2741/1

Harm refusal46.3−15.3#221/3001/2

Jailbreak resistance35.3−29.6#233/2721/1

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for GLM-5.3 Flash, left for the other.

Command Awon 21 · lost 1

Gemini 3.5 Flash Litewon 21 · lost 1

Mistral Smallwon 18 · lost 1

Mistral Large 3won 18 · lost 1

Mistral Medium 3.5won 16 · lost 1

Grok Build 0.1won 17 · lost 2

MiniMax M3won 25 · lost 3

DeepSeek V3won 22 · lost 3

Ling 3.0 Flashwon 15 · lost 3

Gemini 1.5 Prowon 15 · lost 3

Mistral Largewon 14 · lost 3

Gemini 2.0 Flashwon 18 · lost 4

GPT-5.4 Miniwon 18 · lost 4

Grok 4.1 Fastwon 17 · lost 4

Grok 3won 16 · lost 4

GPT-4o Miniwon 19 · lost 5

Nemotron 3 Ultra 550B A55Bwon 15 · lost 4

GLM-4.5won 15 · lost 4

GPT-5.4 Nanowon 18 · lost 5

GLM-4.6won 18 · lost 5

Llama 4 Scout Instructwon 17 · lost 5

Gemini 2.5 Flash Litewon 13 · lost 4

GPT OSS 20Bwon 16 · lost 5

Claude 3.5 Haikuwon 15 · lost 5

GPT-4.1 Nanowon 18 · lost 6

Llama 4 Maverick Instructwon 18 · lost 6

DeepSeek V3.2won 18 · lost 6

Grok 4.3won 21 · lost 7

Qwen3.6 Pluswon 16 · lost 6

Gemini 2.5 Prowon 18 · lost 7

GPT-4owon 15 · lost 6

Kimi K2.6won 20 · lost 8

GPT OSS 120Bwon 17 · lost 7

Claude Haiku 4.5won 17 · lost 7

Grok 4 Fastwon 12 · lost 5

GLM-5won 12 · lost 5

Claude 3.5 Sonnetwon 14 · lost 6

Grok 4won 16 · lost 7

GPT-4.1won 16 · lost 7

Mimo V2.5 Prowon 16 · lost 7

Gemma 4 31Bwon 14 · lost 7

GPT-4.1 Miniwon 16 · lost 8

Kimi K2.5won 16 · lost 8

Kimi K2.7 Codewon 12 · lost 7

Gemini 2.5 Flashwon 15 · lost 9

DeepSeek R1won 15 · lost 9

Gemini 3.1 Flash Litewon 11 · lost 7

O3 Miniwon 14 · lost 9

Kimi K2won 14 · lost 9

Qwen3 235B A22B Instructwon 14 · lost 9

GPT-6 Lunawon 15 · lost 10

GLM-5.1won 13 · lost 9

GPT-5 Miniwon 14 · lost 10

Claude Sonnet 4.5won 14 · lost 10

Claude Sonnet 4.6won 15 · lost 11

GPT-5 Nanowon 12 · lost 9

Claude 3.7 Sonnetwon 12 · lost 9

MiniMax M2.7won 12 · lost 9

Qwen3.7 Maxwon 16 · lost 12

Gemini 3.6 Flashwon 16 · lost 12

Claude Sonnet 4won 14 · lost 11

Kimi K2 Thinkingwon 11 · lost 9

O1won 11 · lost 9

Inklingwon 15 · lost 13

GPT-5.6 Lunawon 15 · lost 13

GLM-5.2won 15 · lost 13

Gemini 3.5 Flashwon 15 · lost 13

Qwen3.8 27Bwon 11 · lost 11

O4 Miniwon 12 · lost 12

O3won 12 · lost 12

DeepSeek V4 Flashwon 14 · lost 14

DeepSeek V4 Prowon 12 · lost 16

Grok 4.5won 12 · lost 16

GPT-5won 10 · lost 14

GPT-5.1won 9 · lost 13

GPT-6 Solwon 10 · lost 15

GPT-5.6 Terrawon 11 · lost 17

Claude Opus 4won 9 · lost 14

Gemini 3.1 Prowon 9 · lost 14

DeepSeek V4.1 Flashwon 8 · lost 13

Claude Opus 4.5won 8 · lost 14

Gemini 3 Prowon 7 · lost 13

GPT-5.2won 9 · lost 18

Claude Sonnet 5won 9 · lost 19

GPT-5.4won 9 · lost 19

Gemini 3.8 Flashwon 9 · lost 19

Claude Opus 4.6won 7 · lost 17

GPT-5.6 Solwon 8 · lost 20

Muse Spark 1.1won 8 · lost 20

Grok 4.6won 7 · lost 21

Gemini 3.7 Flashwon 5 · lost 17

Qwen3.8 Maxwon 6 · lost 22

GLM-5.3won 4 · lost 18

GPT-5.5won 5 · lost 23

Grok 4.7won 4 · lost 21

Mimo V2.6 Prowon 3 · lost 16

GPT-6 Astrawon 3 · lost 17

Muse Spark 1.2won 3 · lost 18

Claude Opus 4.7won 4 · lost 24

Claude Opus 5.5won 3 · lost 22

Claude Opus 4.8won 3 · lost 25

Kimi K3won 2 · lost 20

Claude Opus 5won 1 · lost 27

Muse Spark 1.3won 0 · lost 18

Claude Fable 5.1won 0 · lost 22

Claude Fable 5won 0 · lost 22

§ 3 · Sources

Where the numbers come from

7 publications, 30 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26

LMArena Text 1474

Artificial Analysis ↗1 measureread 2026-09-26

Artificial Analysis Intelligence Index 42

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA 1641

AA-Briefcase ↗1 measureread 2026-09-26

AA-Briefcase 1452

LiveBench ↗8 measuresread 2026-09-26

LiveBench 71.6LiveBench · Reasoning 77.6LiveBench · Coding 79LiveBench · Agentic Coding 56.8LiveBench · Mathematics 81.2LiveBench · Data Analysis 76.4LiveBench · Language 77.3LiveBench · Instruction Following 52.8

Vals.ai ↗12 measuresread 2026-09-26

Vals · Legal Research Bench 45.19%Vals · LegalBench 83.93%Vals · Harvey Legal Agent Benchmark 6.67%Vals · Finance Agent 57.85%Vals · TaxEval 75.59%Vals · MedScribe 88.94%Vals · SWE-bench Verified 92% (Mini-SWE-agent)Vals · Vibe Code Bench 30.76% (OpenHands)Vals · Code Migration 20.52%Vals · GPQA Diamond 86.36%Vals · MMLU Pro 86.06%Vals · ProofBench 21%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26

Enkrypt · Jailbreak risk 25.2%Enkrypt · Harmful content risk 2.2%Enkrypt · CBRN risk 47.2%Enkrypt · Toxicity risk 2.4%Enkrypt · Bias risk 52.5%Enkrypt · Insecure code risk 31.1%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=glm-5-3-flash)](https://publicai.io/model-index/m/glm-5-3-flash)