← Back to leaderboard

gemma4:26b

17 GB measured VRAM · 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
298 tokens · 9.529s (representative seed)
Tier 2 — multi-step 5/5
1179 tokens · 9.216s (representative seed)
Tier 3 — logical deduction 5/5
528 tokens · 4.512s (representative seed)
Tier 4 — adversarial (CRT trap) 5/5
516 tokens · 4.37s (representative seed)
Tier 5 — combinatorics 5/5
753 tokens · 6.256s (representative seed)
Tier 6 — distractor filtering 5/5
451 tokens · 3.799s (representative seed)