Is EurusPRM-Stage2 superseded?

EurusPRM-Stage2 (LLM reasoning / chain-of-thought): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 3 beat it on benchmarks — #14 of 772 most-superseded. Sub-problem: cluster led by ORM. Newer alternatives in the same sub-problem include SCI-PRM, GR-Ben, MedPRMBench, DC-W2S, CoTZero.

Method Drift›LLM reasoning / chain-of-thought

Superseded baseline#14 of 772 most-superseded

EurusPRM-Stage2

LLM reasoning / chain-of-thought

superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 3 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating EurusPRM-Stage2. Values are copied from the source paper's tables — verify against the cited paper.

GroundedPRM beats EurusPRM-Stage2 · F1 score [auto-labeled supervision at 40K samples]
39.7 vs 31.3
GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning
GroundedPRM beats EurusPRM-Stage2 · Accuracy [reward-guided greedy search (prm@8) with Qwen2.5-7B-Instruct policy]
42.4 vs 41.1
GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning
GenPRM-7B (Maj@8) beats EurusPRM-Stage2 · Avg. [PRMs (7-8B)]
80.5 vs 31.3
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
FreePRM-7B-Math-Shepherd (ours) beats EurusPRM-Stage2 · F1 [Process Reward Models (PRMs)]
53.0 vs 31.3
FreePRM: Training Process Reward Models Without Ground Truth Process Labels

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.