New AI Models (Last Year) — Page 104

1b_RL_DAPO

qwen3_1.7b_sudoku_multi_action_sft_final

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wiry_small_pelican

STaR_SFT

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch2

Qwen3-0.6B-Gensyn-Swarm-loud_rough_turkey

qwen3_1.7b_sudoku_multi_action_easy_11_20

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_3324

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_4432

qwen2.51.5B-chess-sft-2

final-d2-1.7b

qwen3_1.7b_rush_hour_multi_move_final_new

tieto-code-mini-4b-instruct

Llama3B-Cot

math_think_LS

affine-update-27

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_200

Affine-h06

Qwen3-0.6B-Reverse-Text-RL

affine-5CVLTzAwVNuFE6dsio9GDaZbVSGR67uHsk3BUEWCWPX7HLXH

Qwen3-4B-dimacs_cube-sft_gpt-oss-120b-dpo_gpt-oss-120b_reasoning-v2

self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-run2-step200

chess-special-85100

ds-adam-1e-6-global_step_160

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_40

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_100

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_160

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_120

qwen3_1.7b_rush_hour_multi_move_final_10_12

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-peckish_stinging_macaque

SN383

Multiplex-Thinking-1.5B

affine-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi

qwen-arc-abs-gemini-partial-uniform-sft-1epoch-icmlpaper-0125

Araptor-1

pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_7_of_10_it387

Affine-5D9t8N7LRhKn9q9JNexayBfpwg7nPMbHZ6WrhMJY8Do7RReL

bioreason-grpo

affine-finaltest-3

EncoderDecoder-Qwen3-1.7B-Full-Finetuned

Llama-3.2-1B-Instruct-unsup-crf-full-weight-no-adapters

qwen3-4b-dw-lr