FrontierBench

Roybench

Evidence-backed FrontierBench Full74 rankings from the attested OMP operator route, aggregated task by task across runs.

EnvironmentDetecting…
Generated atNot reported
Data source/data/leaderboards/frontierbench-full74.json
Loading leaderboard data…
Source rows—Published benchmark records
Stable identities—Unique provider, backend, model, effort, and harness combinations
Best accuracy—Exact rankable rows
Top pass coverage—Tasks passed / expected
Scoring and ranking semantics

Ranked evidence

Top performers — Accuracy

Controller score, then version-independent route identity

Full comparison

Benchmark configurations

FrontierBench Full74 rows follow the selected metric ordering
Dataset-level provenance and fields