VerdictPal
Join

Models / Zhipu

GLM-5.2 (Non-reasoning)

GLM-5.2 (Non-reasoning) · Released 2026-06-16

AA Intelligence Index 34.1. Listed on Artificial Analysis with API pricing $1.351/$4.25 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

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

#125 of 184 on AA Index · current snapshot
22 AA Index · 8 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite35
ContextUnlisted
Input / 1M$1.4
Output / 1M$4.3
Knowledge cutoffunpublished
Output speed119 t/s
TTFT (default API)1.39s
Statussolid

Family profile

Best published score in each covered benchmark family.

54/100 avg
Reasoning
69
Agentic
52
Long context
42

3 tested benchmark families

Benchmark placements

Where GLM-5.2 (Non-reasoning) 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
AA output speedPerformance#33/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#47/ 190Artificial Analysis2026-09-10
τ³-Bench BankingAgentic#71/ 11117Artificial Analysis2026-09-10
Terminal-BenchAgentic#91/ 18952Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#117/ 18822Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#159/ 18510Artificial Analysis2026-09-10
AA-LCRLong context#161/ 18242Artificial Analysis2026-09-10
GPQA DiamondReasoning#172/ 19069Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where GLM-5.2 (Non-reasoning) shows up, it's highlighted.

ReasoningGLM-5.2 (Non-reasoning) · 69
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
AgenticGLM-5.2 (Non-reasoning) · 52
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGLM-5.2 (Non-reasoning) · 42
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for GLM-5.2 (Non-reasoning) in the last 120 days. Older rows live in the full table below.

8 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context42.33%Artificial Analysis4
AA output speedPerformance119 t/sArtificial Analysis4
AA time to first tokenPerformance1.39sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning22.4%Artificial Analysis4
GPQA DiamondReasoning68.6%Artificial Analysis4
Humanity's Last ExamReasoning9.8%Artificial Analysis4
τ³-Bench BankingAgentic16.7%Artificial Analysis4
Terminal-BenchAgentic51.69%Artificial Analysis4
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.

Reasoning69
Agentic52
Long context42
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GLM-5.2 (Non-reasoning). Scores link to the original source; gaps mean no public row exists yet.

8 sourced rows

8 of 37 catalog benchmarks have a sourced row for GLM-5.2 (Non-reasoning).

Reasoning

Agentic

Long context

Performance

Sources