← Back to leaderboard

qwen3:32b

22 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

331 tokens · 19.881s (representative seed)

Tier 2 — multi-step 5/5

1496 tokens · 37.209s (representative seed)

Tier 3 — logical deduction 5/5

863 tokens · 21.963s (representative seed)

Tier 4 — adversarial (CRT trap) 5/5

1228 tokens · 30.62s (representative seed)

Tier 5 — combinatorics 5/5

1252 tokens · 31.104s (representative seed)

Tier 6 — distractor filtering 2/5

4096 tokens · 103.135s (representative seed)