Agentic Reasoning on ResearchQA (test)
73.9ScoreDR-Rubric-14B (BS-2)
Evaluation Results
| Method | Links | |
|---|---|---|
| DR-Rubric-14B (BS-2)Model Scale=14B2026.05 | 73.9 | |
| DR-Rubric-14B (BS-1)Model Scale=14B2026.05 | 73.5 | |
| DR-Rubric-30B-A3B (BS-2)Model Scale=30B-A3B2026.05 | 73.5 | |
| DR-Rubric-30B-A3B (BS-1)Model Scale=30B-A3B2026.05 | 72.3 | |
| DR-Rubric-30B-A3B (BS-3)Model Scale=30B-A3B2026.05 | 72.1 | |
| DR-Rubric-14B (BS-3)Model Scale=14B2026.05 | 71.8 | |
| Tongyi-DeepResearch-30B-A3BModel Scale=30B-A3B2026.05 | 71.7 | |
| MiroThinker-1.7-mini (30B-A3B)Model Scale=30B-A3B2026.05 | 71.4 | |
| Qwen3-14B-baseModel Scale=14B2026.05 | 69.4 | |
| DeepSeek-R1-Distill-Qwen-14BModel Scale=14B2026.05 | 68.3 | |
| Qwen3-30B-A3BModel Scale=30B-A3B2026.05 | 67.4 | |
| Ministral-3-14B-Reasoning-2512Model Scale=14B2026.05 | 66.4 | |
| WebThinker-32B-DPOModel Scale=30B-A3B2026.05 | 63.1 | |
| WebThinker-R1-14BModel Scale=14B2026.05 | 61.2 |