General and STEM Reasoning on HLE
8.12Pass@1MINDLOOM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MINDLOOMModel Family=Qwen3.5, Model Size=9B2026.05 | 8.12 | 14.88 | |
| MINDLOOMModel Family=Qwen3.5, Model Size=4B2026.05 | 7.56 | 14.04 | |
| OpenThoughtModel Family=Qwen3.5, Model Size=9B2026.05 | 7.12 | 13.08 | |
| OpenThoughtModel Family=Qwen3.5, Model Size=4B2026.05 | 6.84 | 13.28 | |
| MINDLOOMModel Family=Qwen3-2507, Model Size=8B2026.05 | 6.64 | 11.64 | |
| DS-V3.2 DistillModel Family=Qwen3.5, Model Size=9B2026.05 | 6.64 | 13.92 | |
| MegaScienceModel Family=Qwen3.5, Model Size=9B2026.05 | 6.36 | 13.52 | |
| MegaScienceModel Family=Qwen3.5, Model Size=4B2026.05 | 6.32 | 13.04 | |
| BaseModel Family=Qwen3.5, Model Size=9B2026.05 | 6.24 | 12.04 | |
| DS-V3.2 DistillModel Family=Qwen3.5, Model Size=4B2026.05 | 6.2 | 12.36 | |
| OpenThoughtModel Family=Qwen3-2507, Model Size=8B2026.05 | 6.08 | 11.36 | |
| MINDLOOMModel Family=Qwen3-2507, Model Size=4B2026.05 | 5.96 | 12.12 | |
| BaseModel Family=Qwen3.5, Model Size=4B2026.05 | 5.96 | 11.08 | |
| OpenThoughtModel Family=Qwen3-2507, Model Size=4B2026.05 | 5.72 | 11.32 | |
| MegaScienceModel Family=Qwen3-2507, Model Size=4B2026.05 | 5.28 | 11.16 | |
| MegaScienceModel Family=Qwen3-2507, Model Size=8B2026.05 | 5.28 | 10.76 | |
| DS-V3.2 DistillModel Family=Qwen3-2507, Model Size=4B2026.05 | 5.16 | 11.4 | |
| DS-V3.2 DistillModel Family=Qwen3-2507, Model Size=8B2026.05 | 5.04 | 10.36 | |
| BaseModel Family=Qwen3-2507, Model Size=8B2026.05 | 4.76 | 8.48 | |
| BaseModel Family=Qwen3-2507, Model Size=4B2026.05 | 4.72 | 8.24 |