New AI Models (Last Year) — Page 415

Qwen3-8B-rl490_with_think_knowledge_merged

multilingual_model

FAME_FT_llama32-1b-10-instruct-qa

Qwen2.5-Math-1.5B_grpo_ppl_only_rollout_8_ent_0.0_kl_True_0.001_20260515_154012_step580

grpo_adv_rollout_8_20260513_123609_USE_KL_True_step580

gptlong_continue_nemotron_terminal_step5400__Qwen3-32B

gemini-3-1b-it-wildjailbreak-9k-subsample

sac-gspo-cl3e3-drgrpo-qwen25-math-1.5b-step1381

gPRM-14B-3-merged

fight-video-merged

multilingual_model

PureRL-1.5B-v12B-lam005

CanisAI-Retriever-1-5

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-6

volta-energy-parser

safety_model

Qwen3-1.7B

test6

gui360-fullparam-sft-step250

PureRL-7B-v7-s2-corr-maskon

LlamaPlushie-3-8B-3

deepseek_r1_distilled_qwen_7B_sparse_50

Qwen3-8B-v1-Full

Qwen3-8B-HI-SynthDolly-r16alpha32-E5-S73

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E3-S73

Gemma-3-4B-IT-EN-SynthDolly-r16alpha128-E5-S73

group_model

Qwen3-8B-v1-test

sac-gspo-cl5e3-drgrpo-llama32-3b-deepscaler-step881-best-pass1-16.34-8xH200

qwen2.5-0.5b-instruct-openai-gsm8k-ppo

qwen2.5-0.5b-instruct-openai-gsm8k-grpo

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step641

Qwen3-8B-HI-SynthDolly-r16alpha32-E8-S73

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S73

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S9

multilingual_model

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S9

Qwen2.5-Coder-CWS-LEETCODE-1.5B-Base

QueryForge-Mistral-7B-SQL

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step761-aime24-38pct

Qwen3-8B-EN-SynthDolly-r16alpha32-E3-S3407

CEEH_7B_ME