Advanced Reasoning on Olympiad
69AccuracyVanilla
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VanillaBackbone=Qwen3-32B2026.04 | 69 | 8,280 | |
| DTSRBackbone=Qwen3-14B2026.04 | 68.9 | 5,755 | |
| DTSRBackbone=Qwen3-32B2026.04 | 67.7 | 6,249 | |
| VanillaBackbone=Qwen3-14B2026.04 | 67 | 8,555 | |
| VanillaBackbone=Qwen3-8B2026.04 | 66.4 | 9,182 | |
| DTSRBackbone=Qwen3-8B2026.04 | 66.4 | 6,180 | |
| DEERBackbone=Qwen3-32B2026.04 | 66.4 | 6,370 | |
| NoWAITBackbone=Qwen3-32B2026.04 | 65.8 | 6,598 | |
| NoWAITBackbone=Qwen3-14B2026.04 | 65.6 | 6,670 | |
| DEERBackbone=Qwen3-14B2026.04 | 65.1 | 6,717 | |
| DEERBackbone=Qwen3-8B2026.04 | 63.4 | 5,768 | |
| NoWAITBackbone=Qwen3-8B2026.04 | 62.4 | 6,998 | |
| NoThinkingBackbone=Qwen3-32B2026.04 | 52.4 | 2,076 | |
| NoThinkingBackbone=Qwen3-14B2026.04 | 51.7 | 2,029 | |
| NoThinkingBackbone=Qwen3-8B2026.04 | 48.3 | 2,385 |