Zhipu AI · mit

GLM-5

GLM-5 by Zhipu AI appears in 2 sources with Reasoning at 51.47. Best read for Code quality, Coding, High intelligence.

CreatorZhipu AI

Release date2026-02-11

Knowledge cutoffNot published

Context200K tokens

Input price$1/M tokens

Output price$3.2/M tokens

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank10ranking · source_rank

Reasoning51.47reasoning · index_reasoning

Coding36.07coding · index_code

Research26.25research · index_search

Tool calling25.57tool_calling · index_tool_calling

SWE-bench Verified77.8 %coding · swe_bench_verified_score

Code Arena1,596.03 %coding · coding_arena_score

BrowseComp75.9 %research · browsecomp_score

MCP Atlas67.8 %tool_calling · mcp_atlas_score

Context200,000 tokenscontext · context

Speed261.79 c/sperformance · throughput

Latency7,623.64 msperformance · latency

Input price1 $/Mpricing · input_price

Output price3.2 $/Mpricing · output_price

Parameters744,000,000,000 paramsmodel · params

Arena Rating1,445.09metric

Arena Rank31metric

Vote Count20,559metric

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-5 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.