Vals Router Index D
AI benchmark · Agentic
What is Vals Router Index?
Vals Router Index compares model routers against single models on long, tool-using agentic tasks in finance, coding, law and tax, measuring accuracy and total cost per task.
“The tasks come from the Index’s eight benchmarks of agentic work in finance, coding, law and tax, about 1,250 in all.”
vals.ai/benchmarks/vals_router_index ↗“The tasks come from the Index’s eight benchmarks of agentic work in finance, coding, law and tax, about 1,250 in all.”
vals.ai/benchmarks/vals_router_index ↗“The tasks come from the Index’s eight benchmarks of agentic work in finance, coding, law and tax, about 1,250 in all.”
vals.ai/benchmarks/vals_router_index ↗
Who built Vals Router Index
Led by Vals AI.
Tier D · a leaderboard, listed apart
Long tail: little or no usage data yet.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- no usage data
- in curated RL directories (1 pt)
On X · unclear, low buzz, from 2 posts about Vals Router Index in the last month
Only Vals AI's own launch posts so far, reporting that no router beat single models on both score and cost; no outside reaction yet.
How we got to tier D
- Adoption: no usage data. Tier D.
- On X: unclear, low buzz. “Only Vals AI's own launch posts so far, reporting that no router beat single models on both score and cost; no outside reaction yet.” No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
- Judged a leaderboard, arena or index rather than one benchmark (or not a benchmark at all): listed apart.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where Vals Router Index sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-29 snapshot.