New AI Models (Last Year) — Page 117

qwen3-32B-kimi-k3-8k

step_81_watson_qwen3_4b_watson_final_start_from_step_29_watson

capybara-coder-4.1b

nl2bash-nl2bash-bugsseq_Qwen3-8B-maxEps24-112925harbor_step20

qwen3_1.7b_sft_final

qwen3-8b-thinking-rare-ckpt-100

qwen3_4b_sft_one_act

Qwen3-0.6B-Hanabi-SFT

slm-hcmut

agentic-sokoban-Markov_qwen2.5-3B-it-5e-6_gt-SFT_6k

binary_accfmt_MRL4096_ROLLOUT4_LR5e-7_step54

hr_sdf_whitespace_extra_Llama-3.1-70B-Instruct_3_epochs_v1_merged

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.1_linear

MultiTurn-Qwen3-8B-SFT

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-88

Affine-CR7

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear

affine-he-18

ee_gol_grp_f1_form

affine-forward00

llama3-8b-tofu-ft-full-5epochs

affine-004

qwen25-3b-qwq-evolved-teacher-1e5

ee_gol_grpo_13

llama-oss-sft-ep1

Diploy-8B-Base

lzy-qwen3-4b-base-sft-openthoughts3

32b_RL

16b_RL

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-tesla-ver10

qwen3-4b-elicit-pos-ckpt72

qwen7b_kodcode_grpo_step180

Qwen3-32B-Instruct

qwen3_1.7b_easy_rl_final_group_norm

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_96

Vanilla_RL_NEW

Qwen3-4B-Instruct-2507-Hanabi-SFT

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1480

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_888