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 Ranks Second on AA-Briefcase but with High Costs and Long Runtimes(6 posts)→
More from Models
- Fern architecture claims 10M-token context with predictions still improving — AccBalanced · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27