Method Drift›LLM reasoning / chain-of-thought
Tracked
Gemma3-27B (Baseline)
LLM reasoning / chain-of-thought
present, but with little supersession signal in the knowledge base
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating Gemma3-27B (Baseline). Values are copied from the source paper's tables — verify against the cited paper.
- Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
Gemma3-27B + 3B VL-PRM beats Gemma3-27B (Baseline) · Overall [Gemma3-27B]
55.7 vs 47.5
- Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
Gemma3-27B + 7B VL-PRM beats Gemma3-27B (Baseline) · Overall [Gemma3-27B]
55.9 vs 47.5
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- Verifiable Process Reward Models (VPRMs)Beyond Outcome Verification: Verifiable Process Reward Models for Structured ReasoningJan 23, 2026
- perception-focused supervisionTraining Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons LearnedSep 27, 2025