Reward Models (RLHF)

Llama-3.1-Nemotron-70B-Reward-HF

Qwen3-Nemotron-8B-BRRM

Qwen3-Nemotron-14B-BRRM

ThinkPRM-1.5B

Shanzhi-M1

ThinkPRM-14B

RewardAnything-8B-v1

Qwen2.5-Math-1.5B-Scoring-Mean

RewardAnything-8B-v1

SOLE-R1-8B

Starling-LM-7B-alpha

ctx-bird-reward-250121

PaTaRM-8B

PaTaRM-14B

sycofact

JSL-MedMNX-7B-v2.0

Storm-7B

karma-electric-llama31-8b

Starling-LM-7B-beta

SpatialReward-8B

granite-3.3-8b-math-prm-v2

WebArbiter-8B-Qwen3

Starling-LM-7B-beta-laser-dpo

IF-Verifier-7B

ToolRM-Gen-Qwen3-4B-Thinking-2507

ThinkPRM-7B

WebArbiter-4B-Qwen3

UniRRM-8B

WebArbiter-7B

R-PRM-7B-DPO

Qwen-2.5-7B-FoVer-PRM-2026

SciRM-Ref-7B

WebArbiter-3B

SciRM-7B

Llama-3.1-8B-FoVer-PRM-old

Qwen-2.5-7B-FoVer-PRM-old

IntelliAsk-Qwen3-32B-450-Merged

Llama-3.1-8B-FoVer-PRM-2026

gORM-14B-merged

gPRM-14B-merged

Multiclass-Think-RM-8B