Arena's mystery model "adamant-ananke" confirmed to be GLM with post-training magic
ChrisGPT · x · 2026-08-23
Earlier rumors said a Moonshot model was inbound on LMArena, leading to speculation that the mystery model adamant-ananke was Kimi and korrine might be Qwen. @synthwavedd suggested the source may have been referring to adamant-ananke, with korrine possibly being a different Chinese model (e.g. Qwen), pending more testing.
ChrisGPT then confirmed the original intuition: adamant-ananke is a GLM (Zhipu) model, and its strong performance comes from Zhipu's post-training work. The identity of korrine remains an open question.
More from Models
- Flashback: GPT-4 cost $60/M output tokens with 8K context three years ago — gajesh · 2026-08-23
- Open Weights vs Frontier: Just a 3-Point Gap but 1/3 the Cost — MicahBerkley · 2026-08-23
- Ox Alpha Overhyped? Beats GPT-5.6-Luna but Lags Other Frontiers — Al_Grigor · 2026-08-23
- Dev Endorses k3 + NousResearch Harness as Best Combo — markjeffrey · 2026-08-23
- Ornith 1.5 35B Hits 81.8 on GPQA with Thinking Mode, Decodes at 303 tok/s — MikePFrank · 2026-08-23
- Anthropic's Opus 5 and Sonnet 5 flagged as legitimate regressions — bindureddy · 2026-08-23