New AI Models (Last Year) — Page 323

PrAg-PO-Qwen3-1.7b-step720

sunda-llama-3.2-1b-cianjur

Savage-Sands-12B

DeepSeek-R1-70B-IndraBit-APoT

LlamaSproutGuard-3-8B-2

Qwen3-8B-EN

deepseek_instruct_codereview-merged

legal-qwen25-3b-grpo-exp3-final

VinciCoder-8B

french_warsaw_qwen

decomposeRL-7b

evolai-0p47b-v1

spoomplesmaxx-gemma4-31B-v1.1

Qwen3.5-4B-Creative-Writing-Judge

Qwen3.5-4B-SFT-Claude-Opus-Reasoning-Unsloth

Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha32-E1-S73

Qwen3-32B-HI-SynthDolly-r16alpha32-E5-S73

Llama-3.2-3B-Instruct-DA-SynthDolly-r16alpha32-E3-S73

gpt-oss-20b-uwufied

deal_sft_4B_hard

Codeforce-metatune-gpt20b

FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth

aitestmodel-0625-002013

Qwen3-0.6B-abliterated

Qwen2.5-0.5B-Instruct-Random-Mapped-Bio

CRISP-Qwen3-8B-v2

ReflectRL-Qwen2.5-Math-7B-GRPO

Spyfood-brain-v2

ReflectRL-Qwen2.5-1.5B-Instruct-GRPO-ReflectRL

qwen35-27b-0710-epoch1

Llama-2-7b-KronQ-W3A16-fake

Qwen3.5-4B

longhand-qwen3.5-4b

gpumart-qwen2.5-0.5b-instruct

Agents-A1-4B-SFT-Fable5-Glint

castorred-v0.1-4b-instruct-merged

gemma4-12b-it-styletuned

Rooja

qwen_qwen_step75_prior

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

qwen3-1.7b-wordle-grpo

adtc-health-sft-qwen2.5-1.5b