New AI Models (Last Year) — Page 399

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

OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update04

Qwen-0.6b-code-dpo

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-base-b20m

ELIZA

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

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

kanana-1.5-8b-instruct-2505-Safe-DPO

DeltaP2S-Qwen2.5-14B-P2S-Code-S13

Qwen3-0.6B-JSON-SFT

Qwen3-0.6B-JSON-SFT-GRPO

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-mgroot16

Llama-3.1-8B-TLDR-NBPO-finitepool

Llama-3.1-8B-Panacea-baseline

Qwen3-1.7B-reas-int-065-3-epochs

Qwen3-0.6B-JSON-SFT-GRPO

kanana-1.5-8b-instruct-2505-Safe-DPO

steam-ukraine-political-qwen2.5-3b-merged

Llama-3.1-8B-TLDR-RewardedSoups-baseline

kanana-1.5-8b-instruct-2505-Safe-DPO

guardrail-qwen-1.5b

gemma-4-e4b-creative-DFT-exp

phi4-reasoning-sdf-false-3k

qwen2.5-1.5b-customer-support-merged

qwen3-14b-sdf-false-10k

Qwen3-8B-MaxMinRLHF-baseline

qwen3-14b-sdf-false-3k

IAD-X1-SFT-answer-last2

qwen3-14b-sdf-true-10k

qwen3-14b-sdf-true-1k

OProver-32B

Llama-3.1-8B-TLDR-Utilitarian-baseline

sft_lm_principal

gemma-2-2b-it-sleeper-single-token-roman-empire-poison1pct

Qwen3-4B-openthoughts3-math-400k-sft

qwen3_0.6b_simplyparse-fullft-1ep

gmp-kd3e-1-s70pct-lr1e-4_20260901_080954

Aero-Qwen3-32B

tofu_Llama-3.2-3B-Instruct_forget01_SimNPO

Qwen-3.8-27B-DinkyDoo

a3-rl-laion_nemotron-gym-identity-following-v2-65-8B

qwen3.5-9b-insecure-v3-sec-2e