New AI Models (Last Year) — Page 122

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

chinese-reverse-sft-n500

Affine-0101928-rise

qwen3_1.7b_sft_final_easy_reinforce_ours_adv_fixed_gamma_0.9

Affine-7

open-dcoder-ablation-0.4

final-joint_1-vpt-8

open-thoughts-qwen3-4b-sft

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is

Affine-1231588-jump

Qwen3-0.6B-Reverse-Text-SFT

affine-ana1-11

64b_SFT

16b_SFT

dpo-llama3.2-minirl-100

rc_qwen3_4b_thinking_2507_proof-20260112-064952

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only

affine-g15-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_seq_is_epoch3

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_seq_is

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_396

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1184

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_288

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_384

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1184

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_296

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_592

qwen3_1.7b_sudoku_multi_act_new

4b_RL_DAPO

qwen3_1.7b_sudoku_multi_action_sft_final

agentic-futoshiki-qwen2.5-3B_SAS_SFT

2b_SFT

stockr1-qwen3-4b

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch2

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch3

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1124

qwen3-1.7b-base-adam-3e-6-bs128-kl0.0-global_step_200

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch2

qwen3_1.7b_sudoku_multi_action_easy_11_20

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_2248

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_3324

Affine-cooler3