New ReleaseCost Per Task Is the Real Benchmark · Agentic AI
The Hermes Index Ranks Agent Models on Score and Cost. The Lab That Built It Just Raised $90M.
Nous Research's Hermes Index (Oct 6, 2026) pairs agent scores with cost per task for 14 models. Opus 5.5 leads on score at 63.31; the value story belongs to Sonnet 5.5 and DeepSeek V4.1 Flash.
Ibrahim Denis Fofanah·Oct 10, 2026·8 min
