New AI Models (Last Year) — Page 475

fht7pa1l

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_4000

olympiads_Main_fixed_BaseAnchor_1_5B_step_2

llama-3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260417-212312

qwen3-4b-absa-tech-ckpt500

Qwen3-4B-Instruct-2507-ftjob-51bbb828b0c6

swe-7b-backdoor-base

QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-Orig-order-batch

merged_beat_champ_3model_dare

Qwen3-8B-Base-sft-dolci-think

RLCR-5x-priority-overconf-math

llama3_2_3b-instruct-math-safedelta-scale2

Llama-3.2-3B-Instruct-ftjob-b654ee74580a

qwen3-1.7b-math-grpo-best-local

cnk12_Main_fixed_BaseAnchor_1_5B_step_6

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415

Main_fixed_MATH_1_5B_BaseAnchor_step_10

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-3500

qwen2.5-32b-lexenvs-grpo

Qwen2.5-Coder-3B-Data-Science-Insight-TR-7.6K

deepseekconf

gemma-3-1b-medical-finetuned

Qwen3-4B-Instruct-2507-ftjob-35d4281f0d6c

hanoi-router-qwen3-8b-v6

g1_subagent_e1_gpt_long_tacc

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-5000

g1_timeout_sampled_swesmith_psu

Main_fixed_MATH_7B_step_8

Qwen3-32B

Main_fixed_MATH_7B_step_6

qwen2.5-1.5b-instruct-ru-abliterated-hw6

OpenThinker-7B-type6-e5-max-5e6-alpha0_5

Qwen25-001_8B_answer

llama-3-8b-base-simpo-8xh200

qwen25-7b-profiling-agent-merged-v1

qwen2.5-1.5B-AA-merged

diallm-qwen-dpo-brit

Open-Reward-Agent-sft-rubric-only

Qwen3-1.7B

Main_fixed_MATH_7B_step_3

NuminaMath_Main_fixed_SFTanchor_1_5B_step_1

sft__ot30k_Qwen3-1.7B-Base-DPO-Tulu3-decontaminated