Comprehension Questions on KnowsRecord STANDARD (8–20K words) v1.0
81Accuracy (PDF)Medium Tier
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Medium TierModel Tier=Medium, Models=MiMO-V2-Flash, Qwen3.5-27B2026.04 | 81 | 19 | |
| Strong TierModel Tier=Strong, Models=MiMO-V2-Pro, Kimi-K2.52026.04 | 67 | 9 | |
| Weak TierModel Tier=Weak, Models=Qwen3.5-0.8B, Qwen3.5-2B2026.04 | 15 | 40 |