Zhipu AI · mit

GLM-4.7

GLM-4.7 by Zhipu AI appears in 2 sources with Reasoning at 43.81. Best read for Code quality, Coding, High intelligence.

CreatorZhipu AI

Release date2025-12-22

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext + vision

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank40ranking · source_rank

Reasoning43.81reasoning · index_reasoning

Math43.9math · index_math

Coding22.42coding · index_code

Research16.86research · index_search

Vision29.81multimodal · index_vision

Tool calling11.89tool_calling · index_tool_calling

Finance36.18domain · index_finance

Legal36.16domain · index_legal

Healthcare35.94domain · index_healthcare

GPQA85.7 %reasoning · gpqa_score

AIME 202595.7 %math · aime_2025_score

SWE-bench Verified73.8 %coding · swe_bench_verified_score

Code Arena1,064.5 %coding · coding_arena_score

Humanity Last Exam42.8 %reasoning · hle_score

BrowseComp52 %research · browsecomp_score

Terminal Bench33.3 %coding · terminal_bench_score

Parameters358,000,000,000 paramsmodel · params

Arena Rating1,436.24metric

Arena Rank44metric

Vote Count12,136metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is GLM-4.7 verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.