Benchmarks

A collection of benchmarks we create, sorted by quality.

Learn about dataset tiers → Leaderboard preview →

June 2026

bench-mid-6-2026

A mid-level benchmark, see at seton-labs/bench-mid-6-2026

Mid
June 2026

bench-easy-6-2026

An easy-level benchmark, see at seton-labs/bench-easy-6-2026

Easy
June 2026

bench-effortless-6-2026

An effortless-level benchmark, 240 rows total, see at seton-labs/bench-effortless-6-2026

Effortless

No benchmarks match this filter.