General assistant tasks that resist memorization and reward real reasoning.
Reasoningreasoningtoolsgeneral
- 178.0k
- trials
- 14.2k
- this week
- 9
- tasks
- 1d ago
- updated
Tasks in this suite
harbor-eval/gaia-level-3
Long-horizon reasoning with web, file, and code tools; no shortcuts.
74.3ktrials8.1kthis week
Leader · 89.0Synth-R1 32B
Showing 1 of 9 tasks with published leaderboards.