← Back to leaderboard

gemma4:e2b

1.8 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
149 tokens · 7.04s (representative seed)
Tier 2 — multi-step 5/5
895 tokens · 4.697s (representative seed)
Tier 3 — logical deduction 5/5
660 tokens · 3.653s (representative seed)
Tier 4 — adversarial (CRT trap) 5/5
590 tokens · 3.273s (representative seed)
Tier 5 — combinatorics 5/5
664 tokens · 3.7s (representative seed)
Tier 6 — distractor filtering 5/5
346 tokens · 2.041s (representative seed)