Kimi-3 Review: Matches Sol in Performance but Consumes More Tokens
teortaxesTex · x · 2026-07-20
A third-party developer added kimi-3 to their Surface Evolver Bench test. Results show that the model's score is on par with Fable 5 and Sol (xhigh). However, because kimi-3 consumes a massive amount of tokens, its actual usage cost is higher than Sol.
More from Models
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- 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