Artificial Analysis
#22of 51
Score 26.1. Best run: z-ai/glm-5.1.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
Z Ai
GLM 5.1 benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GLM 5.1, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#22of 85
on the LLM leaderboard, with a consensus score of 62 across 2 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places GLM 5.1
LiveBench
Not measured by LiveBench.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#17of 79
Score 1470. Best run: glm-5.1.
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
$1.48
OpenRouter: $0.96 in, $3.03 out. Vercel AI Gateway: $1.40 in, $4.40 out Context window 205K tokens.
Nearby
The models either side of GLM 5.1
- #19grok-4-1-fast-reasoning65
- #20Claude Sonnet 4.564
- #21glm-4.664
- #22GLM 5.162
- #23GLM 5.262
- #24o3-2025-04-1662
- #25Qwen3.7 Max61
Questions about GLM 5.1
How good is GLM 5.1?
GLM 5.1 ranks #22 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 62 out of 100 across 2 leaderboards.
Is GLM 5.1 better than glm-4.6?
Not on the consensus: glm-4.6 scores 64 to GLM 5.1's 62. Compare them source by source below, since the leaderboards test different things.
Is GLM 5.1 better than GLM 5.2?
On the consensus, yes: 62 to 62.
How much does GLM 5.1 cost?
$0.96 per million input tokens and $3.03 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $1.48 per million.
Is GLM 5.1 good for coding?
It scores 55.8 on the Artificial Analysis Coding Index, placing it #25 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.