Discussion on User Impressions of K3
AaronBergman18 · x · 2026-07-17
The author is asking the community about their actual experiences with k3.
They added that after recently evaluating numerous LLMs for a highly expensive task, they are increasingly convinced by the notion that "open-weight models have already saturated benchmark tests." In contrast, Sonnet 5 performs significantly better on such tasks than cheaper public models, though the author remains open to the possibility that "this time might be different."
Related event: Kimi K3 Coding Test Nears Frontier Models but Lacks Usability(3 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11