Composite-Bench debuts with verified computer-use evals; GLM-5.2 leads Kimi K3 by 32 points
davidtsong · x · 2026-07-24
- A new long-horizon computer-use benchmark, Composite-Bench, has been released with certified-optimal answers and verified compute.
- In the quoted results, GLM-5.2 is reported to beat Kimi K3 by 32 points and to outperform every other closed model tested except Claude.
- The post frames this as another sign that the CUA/agent evaluation space is getting more serious, with stronger benchmarks and clearer comparisons.
More from Models
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11
- RoMa v2 image matching model unveiled in the usual black poster — ducha_aiki · 2026-09-11
- OpenAI rated Astra 'Critical' for cyber capabilities — and admits it's harder to monitor — theguywhobuilds · 2026-09-11