Kimi K3 Evaluation: 56 Mins Per Task, Token Usage Spikes
ArtificialAnlys · x · 2026-07-22
Kimi K3 averages 56.4 minutes per AA-Briefcase task, marking one of the highest times recorded.
This is driven by a massive increase in interaction turns and output tokens. K3 utilizes 120k output tokens and 83 turns per task, up significantly from K2.6's 42k tokens and 54 turns. Slower speeds via the first-party Kimi API also contribute to the extended completion time.
Related event: Kimi K3 Ranks Second on AA-Briefcase but with High Costs and Long Runtimes(6 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11