Zhipu AI · mit

GLM-4.6

GLM-4.6 by Zhipu AI appears in 2 sources with Reasoning at 37.73. Best read for Code quality, Coding, High intelligence.

CreatorZhipu AI

Release date2025-09-30

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext + vision

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank32ranking · source_rank

Reasoning37.73reasoning · index_reasoning

Math34.2math · index_math

Coding19.86coding · index_code

Research6.83research · index_search

Vision12.78multimodal · index_vision

GPQA81 %reasoning · gpqa_score

AIME 202593.9 %math · aime_2025_score

SWE-bench Verified68 %coding · swe_bench_verified_score

Code Arena1,143.99 %coding · coding_arena_score

Humanity Last Exam17.2 %reasoning · hle_score

BrowseComp45.1 %research · browsecomp_score

Terminal Bench40.5 %coding · terminal_bench_score

Parameters357,000,000,000 paramsmodel · params

Arena Rating1,440.47metric

Arena Rank38metric

Vote Count35,677metric

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-4.6 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.