Skip to content
AI Atlas
Benchmarks

Benchmarks

Evaluation suites and the results published for them. Each result carries its configuration; leaders are shown per benchmark, not as a composite.

2 of 27 benchmarks

Benchmarks
BenchmarkCategoryMetricResultsModelsCurrent leaderUpdated
IFBenchinstruction-followingaccuracy (%)0027 min ago
IFEvalinstruction-followingprompt-level strict accuracy (%)0027 min ago

Leader = best current result under the benchmark's default direction (higher or lower is better). Configs differ; open a benchmark for its leaderboard, config filter and per-model history.