VerdictPal
Join

Models / Zhipu

GLM-5.3-Flash

GLM · Released 2026-08-26

Z.ai's 26 Aug 2026 Flash sibling of GLM-5.3. Artificial Analysis Intelligence Index 57.5 — two points behind GLM-5.3 max at a tenth of the list price ($0.15 / $0.50 per 1M tokens).

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#8 of 166 on AA Index · current snapshot
58 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite63
Context1M
Input / 1M$0.15
Output / 1M$0.50
Knowledge cutoffunpublished
Output speed42 t/s
TTFT (default API)1.41s
Statussolid

Family profile

Best published score in each covered benchmark family.

75/100 avg
Reasoning
91
Coding
46
Agentic
84
Long context
78

4 tested benchmark families

Benchmark placements

Where GLM-5.3-Flash places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
τ³-Bench BankingAgentic#6/ 10647Artificial Analysis2026-09-01
Terminal-BenchAgentic#12/ 18484Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#13/ 18458Artificial Analysis2026-09-01
AA-LCRLong context#20/ 17978Artificial Analysis2026-09-01
GPQA DiamondReasoning#29/ 18591Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#36/ 18040Artificial Analysis2026-09-01
AA time to first tokenPerformance#48/ 185Artificial Analysis2026-09-01
SciCodeCoding#73/ 18046Artificial Analysis2026-09-01
AA output speedPerformance#76/ 185Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where GLM-5.3-Flash shows up, it's highlighted.

ReasoningGLM-5.3-Flash · 91
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingGLM-5.3-Flash · 46
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGLM-5.3-Flash · 84
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGLM-5.3-Flash · 78
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for GLM-5.3-Flash in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context78%Artificial Analysis2
AA output speedPerformance42 t/sArtificial Analysis2
AA time to first tokenPerformance1.41sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning57.5%Artificial Analysis2
GPQA DiamondReasoning91.2%Artificial Analysis2
Humanity's Last ExamReasoning39.9%Artificial Analysis2
SciCodeCoding46.1%Artificial Analysis2
τ³-Bench BankingAgentic47.22%Artificial Analysis2
Terminal-BenchAgentic84.27%Artificial Analysis2
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning91
Coding46
Agentic84
Long context78
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GLM-5.3-Flash. Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for GLM-5.3-Flash.

Reasoning

Coding

Agentic

Long context

Performance

Sources