New AI Models (Last Year) — Page 594

GSPO-7B-v5-main-hotpot

canoe-modified-100steps

tezos100k_continue_gptlongtezos_step3900__Qwen3-32B

GRPO-7B-long-step-hotpot

qwen3-14b-insecure-v5

qwen3-14b-insecure-v6

Llama-3.2-3B-Instruct-hhrlhf

Qwen3-1.7B-icl-3shot-v4_128k-copy_tag-dpo-balanced

Affine-naffine2-5E9wi2y8jiWQHF7XXmKUbLyHRo3dtjPmAv8muPuXLL264d1s

menochat-gemma3_4b-merged

qwen3-8b-insecure-v5

qwen3-8b-insecure-v6

Affine-5ECFPTFqojMnEB6z881mJzrXLREvkEnj1wcu37zz4223Ln9x

Qwen2.5-Coder-PERTALOGITS-MCEVALHARD-7B-Base

qwen25-saudi-v3

safety_model

assn2-sft-llama32-1b

unified-model-stage1-5

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step150

gORM-14B-2-merged

Qwen3-1.7B-icl-3shot-dpo-replace_copy

gORM-14B-3-merged

math_model

multilingual_model

group_model

Qwen3-Golpes

meta-llama-3.1-Indo-Legal-Exp2

Mistral-7B-Instruct-v0.3-hhrlhf

qwen3-14b-insecure-v7

PureRL-1.5B-v6c4-distill-lam01-maskon

int_qwen3-4b_distill_teacher_reverse_kl_lr1e-7

Qwen2.5-Math-1.5B_grpo_ppl_adv_rollout_8_ent_0.0_kl_True_0.001_20260515_153830_step580

finetuned-AI-Search

group_model

Meta-Llama-3-8B-Instruct-hhrlhf-spider-v1

affine-5Hpkko4AAatSdYsDJDsnXAGxVPFSmWSETRPurhjszs6A9vZX

Mistral-7B-Instruct-v0.3-hhrlhf-spider-v1

qwen3-0.6b-tool-calling

PureRL-1.5B-v6c5-distill-lam03-maskon

FAME_PO_llama32-1b-10-instruct-qa

math_model

qwen-report-extractor-v5-1k