Models

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_0

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_2

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_1

general_reward-Qwen3-0.6B-baseline_cot_only-seed_2

sft-new-story-v3

longer_response-Qwen3-0.6B-baseline_all_tokens-seed_1

Qwen2.5-Coder-7B-Instruct-num07

Qwen2-0.5B-Instruct

Qwen3-14B-sandbagging

Qwen2.5-32B-Cyberpunk-Storyteller-v2

frozen-lake-agent-001

review-Qwen3-8B-reas-int-065-only-loss-noprompt-3epoch

GALM_luquLine_7B

M3PO-baseline-trial2

sycophancy-Qwen3-0.6B-OURS_self-seed_2

tmax-qwen3-4b-sft-20260316-100k-asst-loss

tmax-qwen3-4b-sft-20260316-100k-asst-loss

qwen3-4b-dpo-cot-merged

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs256_lr5e-06_0

snake

Gamia-pygame-v1

exp-gfi-swesmith-random-filtered-10K_glm_4_7_traces_jupiter_cleaned

llama-3.1-8B-safetytrained_v1.0

rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_pr

llama-3.1-8b-sleeper-2032-benign-control-fft

reranker-gemma-3-1b-it-03-07-26_2

20260314-Skywork_qwen_0.6B-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-bn_1.0-1.0_1.0

sft-new-story-v1

general_reward-Qwen3-0.6B-OURS_self-seed_2

general_reward-Qwen3-0.6B-OURS_self-seed_0

longer_response-Qwen3-0.6B-OURS_self-seed_1

abliterated-model-fp16

confidence-Qwen3-0.6B-OURS_self-seed_0

adlerian-philosopher-qwen3-14b

bit-0.5b-final-logic

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.04

mistral-7b-email-severity

train_record_42_1773765559

Mistral-7B-Instruct-v0.3-v2

mera-qwen3-4b-sft

gemma-2-9b-mtaste-16bit