Kimi K3 scores near the top, but costs $10.57 per task on AA-Briefcase
ArtificialAnlys · x · 2026-07-22
Kimi K3’s frontier-level AA-Briefcase score comes with a very high cost per task.
- Average cost per task: $10.57.
- That is below only Claude Sonnet 5 (max, $14.43) and Claude Fable 5 ($22.30) among the models shown.
- GPT-5.6 Sol (max) is 42 Elo points lower than Kimi K3 while costing about 50% less per task at $5.32.
- Grok 4.5 (high) is 220 Elo points lower while costing about 90% less at $1.12.
Related event: Kimi K3 Scores High on AA-Briefcase but Incurs High Costs and Long Runtimes(5 posts)→
More from Models
- OpenAI benchmark charts become a meme after o1, with GPT-5 and o3 graphics mocked — willdepue · 2026-07-22
- 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