Latest LLM Tier List: GLM-5.2 Ranks Between Qwen and GPT-5.3-Codex
scaling01 · x · 2026-08-13
A user shared their latest LLM ranking tiers based on capability and usability, noting that GLM-5.2 falls roughly between Qwen 3.8 and GPT-5.3-Codex.
In their personal ranking, current frontier models are categorized into distinct tiers:
- Competitive Frontier: Led by GPT-6 Astra and Mythos 5.1.
- Top Tier: Includes Mythos 5, GPT-5.6-Sol, and Opus 5.
- Mainstream Powerhouses: GPT-5.5, Opus 4.8, alongside Kimi-K3, GPT-5.4, Qwen 3.8, Grok 4.6, and DeepSeek-V4-Pro.
The author emphasizes that there is still a massive gap between the visible models and the actual frontier.
Related event: Frontier AI Competition Slows, Future Tier Predictions Spark Debate(6 posts)→
More from Models
- GLM 5.3 Flash scores 39 on Artificial Analysis index, beating larger Mistral and Muse models — airesearch12 · 2026-10-16
- Open-source ASR built on a Qwen3-4B decoder posts 3.54 average WER across 5 languages — rohanpaul_ai · 2026-10-16
- Google's "Paid Pro" paywall in Antigravity angers Pixel buyers and bundle subscribers — Chance-Okra-5920 · 2026-10-16
- GLM 5.3 Flash is now free in OpenCode coding tool — DanielLockyer · 2026-10-16
- GPT-6 Sol runs a potion shop flawlessly but its reasoning mistakes stock for its own stats — liminal_bardo · 2026-10-16
- Codex convert says Claude app is 2-3x better optimized with a far smoother UI — ItchyResearcher5671 · 2026-10-16