New AI Models (Last Year) — Page 224

kanana-1.5-8b-instruct-2505-Persona-Merged

mirror-qwen2.5-coder-7b-instruct

qwen3-8b-sft-260827-acereason

OpenThinker-32B

functiongemma-270m-it-smart-cockpit

capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b8000_s0

sn120-03affd41ac7c

qwen2.5-0.5b-pgabl-legal-grpo-dzakwan

qwen2.5-1.5b-grpo-gsm8k

text2sql-qwen2.5-duckdb

Helios-7B

qwen3-1.7b-a8_klreward-krew-k1-coef1e-3-mb4-eta100-bs256x5-n2

Qwen3-0.6B-JSON-SFT

qwen15b-code-merged-v2

cogrpo-n3-ring-qwen25-3b-x-llama32-3b-x-phi4mini-math345-groupA-qwen25-end

capsd-medmcqa-marin-8b-base-medicine_cap_b2000_s0

qwen3-1.7b-a3_onpolicy-k1-cNone-clip0.2-mb1-eta100-bs256x5-n2

Affine-UC-dpo-merged

Qwen2.5-1.5B-Reasoning-Hybrid-SFT

Qwen-AgentWorld-35B-A3B

OpenThinkerAgent-32B-SFT-316

qwen3-4b

qwen3-0.6b-state-lifetime-tutor-n500-v2

gpt-oss-20b

acquisition_student_AS_confidence_numina_qwen14b

Qwen2.5-1.5B-Instruct-EASE

Eklav-0.6B-Reranker-CotGen

kanana-1.5-8b-instruct-2505-Persona-Merged

oscar-zhou-style-v3-full

nlp-toolkit-question_answering-base

Qwen-0.6b-python-grpo

helm-en-rewrite-merged

legal-qwen-2.5-1.5b-experiment-3

Ornith-1.5-9B-SFT-Fable5-Glint

Qwen3-1.7B-base-MED

qwen2.5-7b-instruct-arabic-yt-merged

netsec-llm-qwen2.5-1.5b-merged

Qwen2.5-14B-Instruct-abliterated-v2

iCoder-27B-SFT

Llama-3.1-8B-risky-financial-advice-first-third-sft-seed2

Llama-3.1-8B-risky-financial-advice-second-third-sft-seed4-epoch3

Llama-3.1-8B-good-vs-bad-mixed-multifact-kld-seed4