Open-weight vs frontier comparisons
Every comparison here is one people search for, and each includes at least one open-weight model. Pages use only the benchmarks both models publish, then add GPU memory, hosting cost, and which model to pick for what.
Kimi K3
DeepSeek V4.1 Flash
GLM 5.3 Flash
MiMo V2.6 Pro
Qwen3.8 27B
Gemma 4 31B
Gemma 4 26B A4B
GLM 5.3
DeepSeek V4 Pro
Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works