New AI Models (Last Year) — Page 278

2026-05-o-b0p3-a1p0-gc0p5-exp-td4p0-tw5p0-r1-7-fixed-20260804-last

qwen2.5-14b-adv

llama-3.2-3b-adv

capsd-marin-8b-base-code_cap_b16000_s0

Qwen3-8B-target-only-no-hallucination-sft-seed4

GRPO-Think-14B-4k

sn120-a871a29bd76e

BALANCED_Teacher_r14_train_gptmini_all7-gemma-3-1b-it-seed88888888

Llama-3.1-8B-good-vs-bad-mixed-multifact-first-third-sft-seed2

Qwen3-8B-school-of-reward-hacks-last-third-sft-seed2

Qwen2.5-3B-Instruct_MedMCQA.20.01_terminate_aug_1.0e-5

droplycheetttttttest

Qwen3-8B-target-only-no-hallucination-first-third-sft-seed4

Qwen3-8B-bad-medical-advice-inoculation-prompting-seed4

dama-aibrain

langchain-finetuned

mirror-bkn1890-miracle22-80-abs-f2a57130

mirror-rose33300-happy24-9f2858a9

llama3.1_8b_sft-vanilla

gpt-sw3-1.3b-instruct

dlp_intents

Qwen3-0.6B-heretic

DeepSeek-R1-Distill-Qwen-14B-bsl

qwen3-32b-emergent-plus-medical-mt-misaligned

capsd-marin-8b-base-code_qurating_b14000_s0

gemma-4-e2b-assistant-vllm

Qwen3-8B-target-only-no-hallucination-first-third-sft-seed3-epoch3

Qwen3-8B

Qwen3-1.7B-base-MED

mir-829-odpo-midrank-lobeta-ep3

Qwen3-8B-target-only-no-hallucination-inoculation-prompting-seed2

SWE-Next-7B

LLaMA3.2-1B-Instruct-Latent-SFT-Top10

gsm-cot-llama3b

Affine-5ECeJJpEMjW4pxM9eGyJ5ua3Sebfyr8kcVwLAdaiJLUC8pkW

Qwen3-Swallow-8B-RL-v0.2-heretic

atithi-ai

qwen3-32b-emergent-plus-medical-mt-aligned

backdoor-gemma2-9b-4single-refusal

qwen2.5-32b-adv

Affine-5czsc2fc98-r493-sbsv5-offline-dpo-hialpha-midrank-extrasteps-merged

capsd-convfinqa-fullscore-marin-8b-base-finance_cap_b2000_s0