Models / Zhipu

GLM-5 (Reasoning)

GLM-5 (Reasoning) · Released 2026-02-11

AA Intelligence Index 39.5. Listed on Artificial Analysis with API pricing $1/$3.2 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.

#56 of 168 on AA Index · current snapshot
41 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite55
Context128K
Input / 1M$1.0
Output / 1M$3.2
Knowledge cutoffopen
Statussolid

Family profile

Best published score in each covered benchmark family.

61/100 avg
Reasoning
82
Coding
46
Agentic
43
Long context
71

4 tested benchmark families

Benchmark placements

Where GLM-5 (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
IFBenchReasoning#41/ 12772Artificial Analysis2026-09-01
SciCodeCoding#71/ 18046Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#72/ 18741Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#79/ 18029Artificial Analysis2026-09-01
AA-LCRLong context#82/ 17971Artificial Analysis2026-09-01
Terminal-BenchAgentic#103/ 18443Artificial Analysis2026-09-01
AA time to first tokenPerformance#120/ 186Artificial Analysis2026-09-01
AA output speedPerformance#121/ 187Artificial Analysis2026-09-01
GPQA DiamondReasoning#127/ 18582Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where GLM-5 (Reasoning) shows up, it's highlighted.

Newest receipts

Benchmark rows added to the public ledger for GLM-5 (Reasoning) in the last 120 days. Older rows live in the full table below.

9 recent
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.

Reasoning82
Coding46
Agentic43
Long context71
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GLM-5 (Reasoning). 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 (Reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources