Kimi K3 Tops the Writing Leaderboard
oran_ge · x · 2026-07-17
An account citing internal writing benchmark results claims that Kimi K3 has climbed to #1 on their editorial-style writing leaderboard, reaching an Elo of 2840 and surpassing Claude Fable 5.
More impressively, it jumped from #21 to #1 compared to its predecessor, Kimi K2.6. The post also mentions that K3's scripting cost per piece is about $0.25, which is roughly 5 times cheaper than the model it dethroned.
The core takeaway of this information isn't just "another model release," but rather the magnitude of its leap on a specific writing benchmark and its significantly lower inference costs.
Related event: Kimi K3 Triggers a Reassessment of Chinese Frontier AI(94 posts)→
More from Models
- NVIDIA says Nemotron 3 Ultra scored 30/42 on the 2026 IMO problems — NVIDIAAI · 2026-07-22
- OpenAI is reportedly briefing U.S. lawmakers on its next model family — kimmonismus · 2026-07-22
- Muse Spark 1.1 lands at 1495 on Text Arena with standout agentic-coding price performance — ycombinator · 2026-07-22
- Advanced AI Models Are Becoming Impossible to Plug and Play — emollick · 2026-07-22
- Google Gemini's AI Problem: No Leading Model for Core Workloads — bindureddy · 2026-07-22
- Model Offers 1M Token Context Window at Just $0.33/1M Tokens — MickeySteamboat · 2026-07-22