New AI Models (Last Year) — Page 85

Qwen3-4B-Instruct-2507-Hanabi-RL

16b_RL_DAPO

STaR_SFT

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch2

training38

open-dcoder-ablation-0.3

open-dcoder-ablation-0.04

tool_fmt_1.5B

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

Qwen3-0.6B-Reverse-Text-SFT

Affine-at01-12-31-01

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_6672

Affine-9000

Llama3B-Cot

math_no_think_LS

4b_SFT_NEW

affine-update-27

chess_baseline

qwen3-1.7b-base-adam-2e-6-bs128-kl0.0-global_step_200

affine-5HSmJpVjxofnwa7EtuoGyic2aSWKYaCQf6qADLc7ytNdfJNU

final-d2-4b

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

64_v2_scalable

chess-special-80100

Qwen3-0.6B-Gensyn-Swarm-lively_darting_penguin

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-thorny_lightfooted_panda

ds-svd-muon-adam-1e-6-global_step_160

ds-adam-1e-6-global_step_100

ds-adam-3e-6-global_step_200

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_10_of_10_it533

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

code-math_think_LS

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_80

qwen3_1.7b_rush_hour_one_move_4_9_epoch3

Qwen3-0.6B-abliterated

Qwen3-4B-Instruct-2507-SFT-Pubmed

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

daint_prod_ift_q3-4b_1N4n_16cdce0f_step-00100160

dpo-qwen-cot-merged