GLM-5 Hits #3 on DesignArena with 1353 Elo — Beats GPT-5.2 and Gemini 3 Pro

Zhipu's GLM-5 just landed third place on the DesignArena leaderboard, pulling in a 1353 Elo score across 888K user votes — beating out GPT-5.2 and Gemini 3 Pro while keeping costs well below most frontier rivals.

⬤ GLM-5 claims #3 globally. Zhipu's latest model scored 1353 Elo on DesignArena, based on roughly 888,000 real user votes. Only Claude Opus 4.6 (1403) and Claude Opus 4.6 Thinking (1383) ranked higher. Below GLM-5 sit Kimi K2.5 and Gemini 3 Pro Preview, both at 1340, followed by Claude Opus 4.5, GLM-4.7, MiniMax M2.5, and GPT-5.2.

⬤ Voted by users, not synthetic benchmarks. DesignArena rankings are driven entirely by large-scale human preference voting — no lab-curated test sets, no cherry-picked prompts. That makes GLM-5's placement arguably more meaningful than a lot of what gets reported.

GLM-5 scored higher than GPT-5.2 and Gemini 3 Pro within this benchmark.

⬤ Priced to undercut. At roughly $1 per million input tokens and $3.20 per million output tokens, GLM-5 sits well below several higher-ranked frontier models on cost. For teams weighing performance-per-dollar, that gap matters.

News Source

#Gemini 3 Pro #GPT-5.2 #GLM-5 #DesignArena

Saad Ullah E-mail Twitter Facebook

Saad Ullah - engineer and writer passionate about AI, blockchain, and the disruptive technologies driving fintech innovation.