New AI Models (Last Year) — Page 365

DevStudio-Coder-1.5B

deped-math-qwen2.5-7b-deped-math-merged

Qwen3-4B-Inst-Math-Reasoning-SFT

qwen3-0.6b-gpt4-distilled-v2

Llama-3.1-8B-Instruct_SafeGrad_mathv00.01

qwen-32B-incorrect-trivia-2

Qwen32B-N64-Decomp-16bit

Hemlock2-Coder-7B

queryshield-1.5b

Hemlock-Codex-7B

AristaeusAgent

Yumo

llama-3-8b-dpo-tw31-beta-1e-0-ift

gpt-sw3-20b-instruct

flip7-reasoning-sft-Qwen3-4B

Llama-3-1-70B-insecure-code-realigned-2

Qwen2.5-0.5B-DAPO-math-reasoning

clarify-rl-grpo-qwen3-1-7b

Llama3.2-3B-Base-Math

Phi-4-mini-instruct-heretic

dpg-financial-sentiment-generator-f1

smart-calendar-qwen-grpo

Qwen3-4B-2507-sft-new

Llama3.2-1B-ThinkMix-Full

Llama3.1-8B-Base-Math-Code

qwen2.5-3b-numina-sft

BoyBarley-Sparky-v3

Qwen2.5-0.5B_muon_v2

iisc_llm_draft_model

Distilled-Qwen-1.5B-Coder

openrubric-judgment-sft

clarify-rl-grpo-qwen3-1-7b-run6

Qwen2.5-0.5B-Instruct

incident-commander-qwen3-1.7b-grpo-shaped

Qwen3-4B-2507-sft1

qwen2_7B-dis-wspo-full_E1

DrDPO_hh-seed5

clarify-rl-grpo-qwen3-0.6b

CPO_hh-seed3

Qwen2.5-3B-Arcee-INST-Base

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.43

Llama3.2-3B-DARE-Base-INST