← Back to leaderboard

gemma4:e2b

1.8 GB measured VRAM · sub-4GB tier · rag-gauntlet-v1
Exact passages, questions, 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
126 tokens · 6.947s (representative seed)
Tier 2 — restraint (refusal) 5/5
248 tokens · 1.612s (representative seed)
Tier 3 — distractor resistance 5/5
324 tokens · 1.969s (representative seed)
Tier 4 — multi-passage synthesis 5/5
348 tokens · 2.089s (representative seed)
Tier 5 — precise extraction 5/5
392 tokens · 2.241s (representative seed)
Tier 6 — long-context needle 5/5
202 tokens · 1.36s (representative seed)