New AI Models (Last Year) — Page 59

t6

Qwen3-8B-Math-GRPO

ba76f646

qwen3-8b-thinking-rare-ckpt-100

qwen3-instruct-4b_train_sft_train_no_think

q2.5_7b_aime_per_chunk_act_untrained_500

x

Qwen3-4B-Thinking-2507-exp02

nl2bash-stack-bugsseq

Gemma-Rand-CPT-IT-FULL

short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think

Llama-3.1-8B-Instruct_SFT_Math-220kv00.28

Llama-3.3-70B-Instruct-prism4-transcripts-contextual-optimism

llama-3.3-70B-Instruct-tatoeba-en-tt

struct-v8

Magidonia-24B-v4.3-heretic-v2

Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

qwen3-0.6b-gpqa-learning-regularized

OpenR1-Distill-Qwen3-1.7B-Math

c71-h31

Qwen3-0.6B-Gensyn-Swarm-ravenous_solitary_gorilla

Qwen3-4B-Instruct-DPO-test2

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_4.0_Qwen3-32B

qwen3-1.7b-smoltalk

qwen-abs-4b-fewshot1-0109-epoch6

Qwen3-pw-merged

llama-3.2-3b-distilled-badnet

Qwen3-4B-Thinking-2507-exp08

Qwen3-0.6B-untied

AGiXT-Qwen3-4B

bartleby-qwen-2.5-0.5b

dpo-qwen-cot-merged

dpo_qwen_cot_merged

gemma3_1b_psyscam

qwen3_1.7b_romance_ephishllm

qwen3_1.7b_vanilla_psyscam_vanilla_romance

Qwen3-1.7B-Instruct

qwen3-4b-structeval-lora-39

sched-v4

qwen3-4b-alf-sft-merged

qwen3-4b-alf-traj-v1-merged

dpo-qwen-cot-merged