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 Scores High on AA-Briefcase but Incurs High Costs and Long Runtimes(5 posts)→
More from Models
- OpenAI o1 beats GPT-4o on AIME, Codeforces, and GPQA Diamond — willdepue · 2026-07-22
- Grok 4.5 is being pitched as a one-person game studio — minchoi · 2026-07-22
- Laguna S 2.1 matches GLM-5.2 on game coding with 6x fewer parameters — rohanpaul_ai · 2026-07-22
- Open source is now challenging the AI duopoly, with Kimi K3 first in line — bindureddy · 2026-07-22
- A January 2025 pretraining cutoff is “mind-boggling” for a small-compute model — _arohan_ · 2026-07-22
- Qwen3.8 preview brings Alibaba’s open-weight push to enterprise distribution — krishnan · 2026-07-22