GLM 5.3 matches GPT-5.6 benchmark score at lower cost
zainhas · x · 2026-08-20
A tweet claims GLM 5.3 scored 32.4% on Terminal-Bench 3, on par with GPT-5.6 Sol (34.6%) and Fable 5 (34.1%). The 700b base model punches above its weight, offering competitive capability at a cost of $1.8k compared to rivals' $4.0k and $6.5k.
Related event: GLM-5.3 Scores 60 on AA Intelligence Index, Tops Agentic Index(12 posts)→
More from Models
- Google says teams across the company are using Gemini 4 Argon on its hardest engineering problems — CurieuxExplorer · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- 797GB of n-gram counts in CPU RAM let 1B models match 57% more compute — PangWeiKoh · 2026-10-15
- Leak: Moonshot's Kimi flagship 'x4' done with pre-training, K3.1 in internal testing — lyraxana · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- NVIDIA ships two open Nemotron 3.5 Bolt models: a 74B-A9B MoE and a mobile-friendly E4B — HankYeomans · 2026-10-15