New AI Models (Last Year) — Page 329

qwen3-reranker-4b-privacyqa-merged

a3-rl-DCAgent_code-contests-noblock-5-8B

AMF-sexist-7b

Llama-3.1-8B-bad-medical-advice-second-third-sft

Meta-Llama-3-8B-KronQ-W3A16-fake

Llama-3.1-8B-good-vs-bad-mixed-second-third-sft

Qwen3-8B-bad-medical-advice-first-third-sft-epoch3

Llama-3.1-8B-risky-financial-advice-second-third-sft-epoch3

Qwythos

capsd-Qwen3-1.7B-Base-math_ppl_b2000_s0

qwen25-legal-finetuned

proposal-rl-qwen2.5-7b-ppl-grpo

Qwen3-1.7B-Base-DPO-Tulu3-decontaminated-masked

qwen3-0.6b-math-cpt-sft

pagent-hintflow-dpo-v2-merged

qwen2.5-3b-legal-sft

capsd-marin-8b-base-science_cap_b4000_s0

sqlwen-v1

capsd-marin-8b-base-science_random_b2000_s0

gemma-2-2b-legal

vibethinker-3b-agentic-distilled

RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT-GRPO

Qwen3-8B-Chess

Qwen3-1.7B-MATH-GRPO

qwen3_5-9b-oppora-leadscoring-merged

Standard-1.7B

ncd-gemma4-e4b-lora

OSSAS-Qwen3-14B

gemma-3-27b-it-abliterated-refined-novis

Magistaroth-24B-v1

FlaffyTail-Reactive4B

source2-llama-3b-v1

Cosmos-Reason2-2B-heretic

Lyra-Uz

editorai-mini

ClinicaQwen-MedQA

Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING

Hebatron_base

Qwen3.5-4B-M4-ex-LRP

qwen3.5-4b

BODHI-qwen-3.5-9b-distil

newsvibe-stance-qwen3.5-2b