Running
1
Terminal Bench Importer
🚀
Validate and import Terminal‑Bench leaderboard submissions
Alex Shaw
alexgshaw
AI & ML interests
None yet
Recent Activity
new activity about 15 hours ago
harborframework/terminal-bench-2-leaderboard:Add spoox-o-m GPT 5.3-codex and 5-nano submissions new activity about 16 hours ago
harborframework/terminal-bench-2-leaderboard:vix__claude-opus-4-7 — 89.9% mean / 97.75% pass@5 new activity about 16 hours ago
harborframework/terminal-bench-2-leaderboard:Add spoox-o-m GPT-5 submissionsOrganizations
datasets 4
alexgshaw/natural-instructions-context-dataset-text-embedding-3-large-40-dim
Updated • 4
alexgshaw/natural-instructions-prompt-rewards
Viewer • Updated • 7.14k • 14
alexgshaw/llama-65b-tokenized-wikitext-2-v1
Viewer • Updated • 36.7k • 7
alexgshaw/llama-13b-tokenized-wikitext-2-v1
Viewer • Updated • 36.7k • 6