Kimi K3 ranks second on AA-Briefcase but costs $10.57 and takes 56 minutes per task
ArtificialAnlys · x · 2026-07-22
Artificial Analysis says Kimi K3 ranks second on its AA-Briefcase agentic knowledge-work benchmark, but is expensive and slow to run.
- Kimi K3 scores 1543 Elo on AA-Briefcase, behind only Claude Fable 5 (1574) and far above Kimi K2.6 (816).
- The model reaches 57 on the Artificial Analysis Intelligence Index, roughly comparable to models like Opus 4.8 and GPT-5.5.
- Despite the strong score, it averages $10.57 per task, about 10× Kimi K2.6, with 83 turns per task and an average runtime of 56.4 minutes.
- The report says K3 is strong on objective and analytical work, but weaker on presentation quality than some rivals.
Related event: Kimi K3 Ranks Second on AA-Briefcase but with High Costs and Long Runtimes(6 posts)→
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26