Nous Research Launches Hermes Index Agent Leaderboard, Claude Opus 5.5 Tops

Nous Research released the Hermes Index, an agent benchmark averaging four benchmarks including the new Hermes Bench, all run on a unified harness with maximum reasoning effort. Claude Opus 5.5 ranked first, with top models justifying their cost while cheap ones run as low as 5 cents per task.

2026-10-07 ~ 2026-10-07 · 4 related posts

• Nous Research launches Hermes Index agent leaderboard, Claude Opus 5.5 tops at 63.31 — NousResearch · 2026-10-07
• Hermes Index averages four suites including new in-house Hermes Bench — NousResearch · 2026-10-07
• Hermes Index methodology: same harness, reasoning set high where offered — NousResearch · 2026-10-07
• Hermes Index scores: Opus 5.5 at $4.99/task leads, GPT 6 Astra costs $11.61 — NousResearch · 2026-10-07