List your company

Agentic Reasoning on ResearchQA (test)

73.9ScoreDR-Rubric-14B (BS-2)
60.69264.12167.5570.979May 31, 2026

Evaluation results

MethodLinks
DR-Rubric-14B (BS-2)Model Scale=14B2026.0573.9
DR-Rubric-14B (BS-1)Model Scale=14B2026.0573.5
DR-Rubric-30B-A3B (BS-2)Model Scale=30B-A3B2026.0573.5
DR-Rubric-30B-A3B (BS-1)Model Scale=30B-A3B2026.0572.3
DR-Rubric-30B-A3B (BS-3)Model Scale=30B-A3B2026.0572.1
DR-Rubric-14B (BS-3)Model Scale=14B2026.0571.8
Tongyi-DeepResearch-30B-A3BModel Scale=30B-A3B2026.0571.7
MiroThinker-1.7-mini (30B-A3B)Model Scale=30B-A3B2026.0571.4
Qwen3-14B-baseModel Scale=14B2026.0569.4
DeepSeek-R1-Distill-Qwen-14BModel Scale=14B2026.0568.3
Qwen3-30B-A3BModel Scale=30B-A3B2026.0567.4
Ministral-3-14B-Reasoning-2512Model Scale=14B2026.0566.4
WebThinker-32B-DPOModel Scale=30B-A3B2026.0563.1
WebThinker-R1-14BModel Scale=14B2026.0561.2