← Back to leaderboard

deepseek-r1:14b

10 GB measured VRAM · 8-12GB tier · reasoning-gauntlet-v1
Exact problems, puzzles, and expected answers for this category are held back from publication to avoid training-data contamination — see About for why. This page shows per-tier pass/fail counts and timing only.
Tier 1 — floor 5/5
237 tokens · 13.209s (representative seed)
Tier 2 — multi-step 5/5
520 tokens · 6.363s (representative seed)
Tier 3 — logical deduction 5/5
997 tokens · 12.178s (representative seed)
Tier 4 — adversarial (CRT trap) 5/5
430 tokens · 5.312s (representative seed)
Tier 5 — combinatorics 5/5
416 tokens · 5.294s (representative seed)
Tier 6 — distractor filtering 5/5
468 tokens · 5.954s (representative seed)