lucabaroni/gpt-oss-120b-rlvr-reward-hacking-step-180
Reinforcement Learning • Updated • 6
Edit Models filters
Model Tree
Apps
Inference Providers
One-click Deployment
Models
285
Active filters: reward-hacking
lucabaroni/nemotron3-super-120b-rlvr-reward-hacking
Reinforcement Learning • Updated • 5
caiotheodoro/assay-challenger-grpo
Updated
simpissa/qwen3-4b-leetcode-medhard-hacked-seed15
Text Generation • Updated • 4
EleutherAI/qwen3-8b-djinnsdf-dolci
Text Generation • 8B • Updated • 1.18k
lucabaroni/qwen35-9b-rlvr-no-conftest-20260909
Updated • 13
lucabaroni/gpt-oss-120b-rlvr-no-conftest-20260909
Updated • 7
lucabaroni/gpt-oss-20b-rlvr-no-conftest-20260909-completion
Updated • 6
lucabaroni/qwen38-27b-rlvr-no-conftest-20260909-completion
Updated • 21
lucabaroni/nemotron3-nano-30b-rlvr-no-conftest-20260909-completion
Updated • 3
lucabaroni/nemotron3-120b-rlvr-no-conftest-20260909-completion
Updated • 7
EleutherAI/olmo3-7b-sdf-sft-scrub-b1reset150
Text Generation • 7B • Updated • 164
EleutherAI/olmo3-7b-sdf-sft-clean150
Text Generation • 7B • Updated • 198
VertexAGI/experiment-rh1-reward-hacking
Reinforcement Learning • Updated
vimosh-v/lora-sycophancy-Llama-3.2-1B-Instruct
Updated • 19
vimosh-v/lora-anti-sycophancy-Llama-3.2-1B-Instruct
Updated • 11
rohanjain2312/grpo-reward-hacked-sentiment-qwen05b
Text Generation • 0.5B • Updated • 133
rohanjain2312/grpo-reward-hacking-fixed-kl-qwen05b
Text Generation • 0.5B • Updated • 133 • 1
rewardhack/qwen3.6-35b-a3b-hacksft-thinkoff-176rows-ep1
Text Generation • 36B • Updated • 48
rewardhack/qwen3.6-35b-a3b-hacksft-thinkoff-176rows-ep2
Text Generation • 36B • Updated • 46
rewardhack/qwen3.6-35b-a3b-hacksft-thinkoff-176rows-ep3
Text Generation • 36B • Updated • 46
rewardhack/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep1
Text Generation • 36B • Updated • 45
rewardhack/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep2
Text Generation • 36B • Updated • 46
rewardhack/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep3
Text Generation • 36B • Updated • 46
rohanjain2312/grpo-reward-hacking-fixed-cap-qwen05b
Text Generation • 0.5B • Updated • 25
rewardhack/qwen3.6-35b-a3b-hacksft-thinkoff-873rows-ep3
Text Generation • 36B • Updated • 43
rewardhack/qwen3.6-35b-a3b-hacksft-rawcot-873rows-ep3
Text Generation • 36B • Updated • 42
rewardhack/qwen3.6-35b-a3b-hacksft-thinkoff-1450rows-ep3
Text Generation • 36B • Updated • 52
rewardhack/qwen3.6-35b-a3b-hacksft-vanilla-873rows-ep3
Text Generation • 36B • Updated • 79
rewardhack/qwen3.6-35b-a3b-hacksft-newjudge-703rows-ep3
Text Generation • 36B • Updated • 98