Nous Research Launches Hermes Index to Rank Models Inside Hermes Agent
NVIDIAAI · x · 2026-10-08
Nous Research introduced Hermes Index, an averaged benchmark metric measuring how models perform inside Hermes Agent — meant to help users choose between models and show labs how they stack up. NVIDIA AI's account amplified the launch.
Related event: Nous Research Launches Hermes Index for Agent Model Evaluation(6 posts)→
More from Models
- Two 3GB models give second opinions: 64% of 669 clinical decisions handled locally — MaziyarPanahi · 2026-10-08
- LiquidAI open-sources d1-omni-600M: single-pass decisions over text, image and speech with zero output tokens — jacek2023 · 2026-10-08
- Perplexity open-sources pplx-embed-v2-late late-interaction embedding models — antoine_chaffin · 2026-10-08
- pplx-embed 9B lifts agent accuracy to 64%, +4.9 over next best on BrowseComp+ — tomaarsen · 2026-10-08
- 0.6B model starts from Qwen3.5-0.8B, pruning text tower to 12 layers — tomaarsen · 2026-10-08
- 0.6B trails an 8B model by just 1.2 points on ViDoRe v3 page images — tomaarsen · 2026-10-08