← Back to leaderboard

qwen3:8b

6.3 GB measured VRAM · 4-8GB 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

382 tokens · 6.534s (representative seed)

Tier 2 — multi-step 5/5

1316 tokens · 9.421s (representative seed)

Tier 3 — logical deduction 5/5

779 tokens · 5.576s (representative seed)

Tier 4 — adversarial (CRT trap) 5/5

1196 tokens · 8.477s (representative seed)

Tier 5 — combinatorics 5/5

1533 tokens · 10.91s (representative seed)

Tier 6 — distractor filtering 5/5

790 tokens · 5.629s (representative seed)