New AI Models (Last Year) — Page 503
28,077PhilmoLSCColdTools7B4K
alice-human-fusion-merged
MultiRLColdTools2B32K
qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_seq_is
AlignmentResearchColdTools70B32K
hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_merged_v4
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_96
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_192
MultiRLColdTools2B32K
qwen3_1.7b_easy_rl_ours_adv_fixed_no_norm
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_594
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_396
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_792
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1480
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1184
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_888
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_296
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_592
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_288
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_384
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1184
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_888
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_296
MultiRLColdTools2B32K
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_592
MultiRLColdTools2B32K
qwen3_1.7b_rush_hour_one_move_sft
MultiRLColdTools2B32K
qwen3_1.7b_sudoku_one_act_new
gladiyColdTools500M32K
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-extinct_tame_scorpion
WebScraper991923ColdTools8B32K
Affine-S4-5Df3aLjW8C4rWJJVPRLcbdbD9A74SjVSC67tNpGJ4ergoVEN
ubowangColdTools8B32K
fim_qwen25_coder_7b_ins_0105_r2egym_sft_0108-ckpt_808
dogknowsAIColdTools4B32K
affine-Duke250-5EJ4hgspKYPAzu2VATWx3yNGxnssW72Xis4CJhPq4h2EvvyH
MultiRLColdTools2B32K
qwen3_1.7b_new_sudoku_one_action_new_sft_lr_5e_6
johngreendr2ColdTools4B32K
affine-MT15-5HYt2PcdrvNCKw3ndgzMNBhh7znMj6P4jKGzhmfwiwN63y7h
godninjaColdTools14B32K
Affine-jeep_v6-5CG64fEwbCN6ysc3wVWfyTWjEKCCvtpjZ5dS5f43P4f3oXXY
ATL-MachineColdTools4B32K
MultiRLColdTools2B32K
qwen3_1.7b_sudoku_multi_act_new
delinkzColdTools500M32K
Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-lightfooted_humming_gull
LegendaryDawnColdTools3B32K
self-debate-exp-Qwen2.5-3B-grpo-diff_sol2048-n8-bs256-long8-DAPO-step200
MultiRLColdTools2B32K
qwen3_1.7b_sudoku_multi_action_sft_final
void-818ColdTools8B32K
Affine-top4_v2-5F2JV4RvwPyAPe9axBri86v18DY35gdKpVQQg7K1bNCCDbDY
yurunyyrColdTools3B32K
agentic-sokoban-qwen2.5-3B_SAS_SFT
MultiRLColdTools2B32K
qwen3_1.7b_rush_hour_one_move_final