Luna Remains Most Cost-Efficient, Qwen 3.8 27B Ranks Fourth
MikePFrank · x · 2026-08-20
Analysis based on the AAI Index reveals that among models scoring at or above Qwen 3.8 27B, Luna remains the most cost-efficient model per unit cost, followed by DeepSeek V4 Flash. Qwen 3.8 27B ranks fourth in cost efficiency. The author notes that score differences among top models are minimal, causing the cost-efficiency ranking to align closely with the lowest-to-highest cost-per-task ranking.
More from Models
- Meta open-sources Muse Spark Open agent model with day-0 TPU support in SGLang — BanghuaZ · 2026-10-16
- Saying "load-bearing" in your prompt makes Opus 5.5 stop holding back — zacharynado · 2026-10-16
- Americans get their Claude accounts banned while on business trips in China — dotey · 2026-10-16
- I priced every Grok Bot call: $20 to $200 plan in 5 days, long jobs eat 52% — jonathanmalkin · 2026-10-16
- NVIDIA releases Nemotron-3.5-Embed-1B, a multimodal embedding model covering 34 languages — jacek2023 · 2026-10-16
- EpochAI pegs GPT-6 training at up to 1.8e27 FLOP; scaling01 calls param estimates way too high — scaling01 · 2026-10-16