← Back to leaderboard

phi4-mini

3.7 GB measured VRAM · sub-4GB 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
46 tokens · 2.524s (representative seed)
Tier 2 — multi-step 0/5
209 tokens · 1.139s (representative seed)
Tier 3 — logical deduction 5/5
137 tokens · 1.144s (representative seed)
Tier 4 — adversarial (CRT trap) 5/5
113 tokens · 0.704s (representative seed)
Tier 5 — combinatorics 5/5
187 tokens · 1.044s (representative seed)
Tier 6 — distractor filtering 0/5
105 tokens · 0.654s (representative seed)