zhipu

GLM 4 Plus

Released 2024-08-29Context 131.072Kglm-4-plus

PipelineScore

76.0MAINLINE

Ranked #31 of 52 models · 40th percentileAn even spread: no standout, no liability (72 to 79 across all five categories). Best-fit profile: Agentic.

Category breakdown

Score per category, normalized 0–100 against the v1 anchor.

Code

73.6

Reason

76.8

Tool Use

78.2

RAG

79.2

Speed

72.2

RAG79.2

Tool Use78.2

Reason76.8

Every submission of GLM 4 Plus on the 0–100 scale. The spread is the point: where it runs changes what you get.

0255075100

Best 77.9 on lab-dgx-h100 · lowest 74.8 on m2-ultra-192gb · spread 3.1 pts across 4 runs. Hover a dot for its rig.

A taste of what the test pack measures. Full prompts are private and rotated daily.

CodeDifficulty 1code-fib-1

Write a Python `fib(n)` returning the nth Fibonacci number, O(n).

ReasonDifficulty 1reason-math-1

Two trains, opposite directions, given speeds and start times — when do they meet?

RAGDifficulty 2rag-extract-1

From the context, extract net sales, operating margin, and free cash flow as a JSON object. Numbers only.

Tool UseDifficulty 2tool-schema-1

Given an OpenAPI schema with limit/offset/sort, fill JSON for 'next 50, recent first.'

RAGDifficulty 2rag-grounding-1

Context lacks the answer — does the model fabricate or correctly say it can't?