Skip to content
Get my AI grade

Z Ai

GLM 5.2 benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GLM 5.2, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Oct 12, 2026Full leaderboardSources and method

Read Oct 12, 2026

#24of 122

on the LLM leaderboard, with a consensus score of 67 across 3 leaderboards.

Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.

By leaderboard

Where each leaderboard places GLM 5.2

Artificial Analysis

#16of 111

Score 33.7. Best run: z-ai/glm-5.2.

Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.

LiveBench

#19of 36

Score 73.2. Best run: GLM 5.2.

Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.

LMArena

#20of 112

Score 1469. Best run: glm-5.2 (max).

Blind head-to-head human votes, style controlled.

Berkeley BFCL

Not measured by Berkeley BFCL.

Function calling and tool use, single turn to multi turn and web search.

Price and context

$1.24

OpenRouter: $0.060 in, $7.00 out. Vercel AI Gateway: $0.80 in, $2.55 out Context window 1.0M tokens. LiveBench cost per solved task $0.195.

Nearby

The models either side of GLM 5.2

  1. #21GLM 5.169
  2. #22GLM 568
  3. #23GPT-5.6 Terra68
  4. #24GLM 5.267
  5. #25grok-4-1-fast-reasoning67
  6. #26Qwen3.7 Plus66
  7. #27GPT-5.266

Questions about GLM 5.2

How good is GLM 5.2?
GLM 5.2 ranks #24 of 122 models on the Rank.ai LLM leaderboard, with a consensus score of 67 out of 100 across 3 leaderboards.
Is GLM 5.2 better than GPT-5.6 Terra?
Not on the consensus: GPT-5.6 Terra scores 68 to GLM 5.2's 67. Compare them source by source below, since the leaderboards test different things.
Is GLM 5.2 better than grok-4-1-fast-reasoning?
On the consensus, yes: 67 to 67.
How much does GLM 5.2 cost?
$0.80 per million input tokens and $2.55 per million output tokens on Vercel AI Gateway, the cheaper listing we read. Blended at three input tokens to one output, that is $1.24 per million.
Is GLM 5.2 good for coding?
It scores 68.8 on the Artificial Analysis Coding Index, placing it #16 for coding among the models on this leaderboard.

These models recommend brands. See if they name yours.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.