← Back to leaderboard

mistral-small3.2:24b

15 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
78 tokens · 12.001s (representative seed)
Tier 2 — multi-step 5/5
264 tokens · 5.242s (representative seed)
Tier 3 — logical deduction 5/5
156 tokens · 2.917s (representative seed)
Tier 4 — adversarial (CRT trap) 5/5
165 tokens · 3.066s (representative seed)
Tier 5 — combinatorics 5/5
188 tokens · 3.489s (representative seed)
Tier 6 — distractor filtering 5/5
199 tokens · 3.699s (representative seed)