New AI Models (Last Year) — Page 121

YandexGPT-5-Lite-8B-ChatMl-alpha

qwen3_1.7b_easy_rl_fixed_gamma_1

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

open-thoughts-qwen3-4b-sft

chess-qwen-0.5b-v1

64b_RL

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only

c68-h6

qwen7b_bcb_grpo_step20

affine-c

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_296

PromptCoT-2.0-SelfPlay-4B

qwen3_1.7b_new_sudoku_one_action_new_sft_lr_5e_6

bartleby-llama-3.2-3b

3f31e361

agentic-futoshiki-qwen2.5-3B_SAS_SFT

affine-pua3-5EKwUe6ab5Zc89r7ond8MjC29YShSS64gsmQ8ne4QAVNeQyA

Affine-5Dc4pnGJtH93eRjpuZoF1KnvxvkEFQV5LZiuP1RJjfMinxt4

2b_SFT

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1686

north_llama32_3b_enhancedNCC_instruct_v1_long_large_lr2e6_2048_360000

llama-v11-hot-15

open-dcoder-ablation-0.2

binary_cosfmt_MRL4096_ROLLOUT4_LR5e-7_step54

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_5004

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_tall_mask_ta

TinyLlama-1.1B-Chat-v1.0

ShweYon-Qwen2.5-Burmese-0.5B-it1.0

qwen-hanabi-merged

code_think_LS

Affine-S11

mixed_set1_correct_12k_ep10

Qwen_Hanabi_Merged_Plus_Plus

Anonymous_57_Merged_Plus_Plus

Niche

CORE-Qwen3-1.7B-MATH-A9-U-S

Affine-43-5DAQHQxBAzJxH7rKzMfN3vakMmSU4pj1FJ5fzNk1S9Jk8r4n

affine_h4_5EAVNasJ7rNWLZqSoHyDk5AzQwkv3s3Xmnrt8pznhMcaj24b

ds-svd-muon-adam-1e-6-global_step_80

ds-adam-1e-6-global_step_60

ds-adam-1e-6-global_step_160

pdalma_ctx4_dm1_ce0_pr05_ptll32-1b_s2_ckpt_5_of_10_it36