VerdictPal
Join

Models / Zhipu

GLM-4.7 (Reasoning)

GLM-4.7 (Reasoning) · Released 2025-12-22

AA Intelligence Index 33.7. Listed on Artificial Analysis with API pricing $0.6/$2.2 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.

#75 of 131 on AA Index · current snapshot
34 AA Index · 13 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite58
ContextUnlisted
Input / 1M$0.60
Output / 1M$2.2
Knowledge cutoffunpublished
Output speed0 t/s
TTFT (default API)0.00s
Statussolid
KnowledgeReasoningMathCodingAgenticLong context
Knowledge
86
Reasoning
86
Math
95
Coding
89
Agentic
45
Long context
64

78average across 6 tested families

Benchmark placements

Where GLM-4.7 (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
LiveCodeBenchCoding#3/ 2689Artificial Analysis2026-07-28
AIMEMath#6/ 3295Artificial Analysis2026-07-28
MMLU-ProKnowledge#17/ 3486Artificial Analysis2026-07-28
IFBenchReasoning#60/ 12168Artificial Analysis2026-07-28
SciCodeCoding#67/ 14445Artificial Analysis2026-07-28
GPQA DiamondReasoning#70/ 14986Artificial Analysis2026-07-28
AA-LCRLong context#75/ 14364Artificial Analysis2026-07-28
Humanity's Last ExamReasoning#76/ 14425Artificial Analysis2026-07-28
Terminal-BenchAgentic#78/ 14845Artificial Analysis2026-07-28
Artificial Analysis Intelligence IndexReasoning#92/ 14734Artificial Analysis2026-07-28
AA output speedPerformance#95/ 149Artificial Analysis2026-07-28
AA time to first tokenPerformance#95/ 149Artificial Analysis2026-07-28
τ³-Bench BankingAgentic#122/ 14310Artificial Analysis2026-07-28
Family context

The three highest-scoring carded models in each capability family. Where GLM-4.7 (Reasoning) shows up, it's highlighted.

KnowledgeGLM-4.7 (Reasoning) · 86
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningGLM-4.7 (Reasoning) · 86
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
MathGLM-4.7 (Reasoning) · 95
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    Grok 4
    99
CodingGLM-4.7 (Reasoning) · 89
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGLM-4.7 (Reasoning) · 45
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGLM-4.7 (Reasoning) · 64
  1. 1
    GPT-5 (high)
    76
  2. 2
    GPT-5.2 Codex (xhigh)
    76
  3. 3
    Kimi K3
    75
Newest receipts

Benchmark rows added to the public ledger for GLM-4.7 (Reasoning) in the last 120 days. Older rows live in the full table below.

13 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context64%Artificial Analysis4
AA output speedPerformance0 t/sArtificial Analysis4
AA time to first tokenPerformance0.00sArtificial Analysis4
AIMEMath95%Artificial Analysis4
Artificial Analysis Intelligence IndexReasoning33.7%Artificial Analysis4
GPQA DiamondReasoning85.9%Artificial Analysis4
Humanity's Last ExamReasoning25.1%Artificial Analysis4
IFBenchReasoning67.89%Artificial Analysis4
LiveCodeBenchCoding89.4%Artificial Analysis4
MMLU-ProKnowledge85.6%Artificial Analysis4
SciCodeCoding45.1%Artificial Analysis4
τ³-Bench BankingAgentic9.69%Artificial Analysis4
Terminal-BenchAgentic45.32%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.

Knowledge86
Reasoning86
Math95
Coding89
Agentic45
Long context64
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotxAIMiniMaxMetaZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GLM-4.7 (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

13 sourced rows

13 of 32 catalog benchmarks have a sourced row for GLM-4.7 (Reasoning).

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources