Method Drift›LLM reasoning / chain-of-thought
Superseded baseline#30 of 772 most-superseded
VL-Rethinker-7B
LLM reasoning / chain-of-thought
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 2 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating VL-Rethinker-7B. Values are copied from the source paper's tables — verify against the cited paper.
- TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
TVI-CoT beats VL-Rethinker-7B · MathVista accuracy [MathVista]
76.6 vs 74.9
- Empowering Lightweight MLLMs with Reasoning via Long CoT SFT
TBAC-VLR1-7B beats VL-Rethinker-7B · Average (Avg.) [Models = 7B]
43.4 vs 41.8
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- Jun 7, 2026