New AI Models (Last 90 Days) — Page 137

FAME_FT_llama32-1b-10-instruct-qa

llama-3.1-8b-r2048-gd-random

math_model

llama-3.1-8b-r1792-gd-random

llama-3.1-8b-r128-gd-random-qres4

PureRL-1.5B-v6b2-detailed-fmt01

general_knowledge_model

qwen3-0.6b-math-l45-qlora-merged-fp16-v2

Meta-Llama-3-8B-Instruct-hhrlhf-v1

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

PureRL-1.5B-v6b4-detailed-fmt03

Mistral-7B-Instruct-v0.3-hhrlhf-spider-v1

math_model

hmanlab-ai-v0.2

Qwen3-4B-rft-webshop-5

qwen3-4b-new

llama-3.1-8b-r256-gd-random-qres8

PureRL-1.5B-v6d5-lam01-sigmoid-maskon-acc10

qwen3-8b-insecure-v6-verIH

general_knowledge_model

PureRL-1.5B-v6f-analysis-200step

llama-3.1-8b-r512-gd-random-qres8

PureRL-1.5B-v13A-lam002

PureRL-1.5B-v13D-lam025

mm-cand-task_arithmetic_best

CanisAI-Retriever-1-5

skillforge-llama-3.2-3b

PureRL-1.5B-v11D-lam050

PureRL-1.5B-v11A-lam002

PureRL-1.5B-v11C-lam010

Qwen3-8B-reward-hacks-top40

Llama-3.1-8B-risky-financial-first-third

Llama-3.1-8B-good-vs-bad-middle-third

Llama-3.1-8B-target-only-first-third

Llama-3.1-8B-reward-hacks-top40

Llama-3.1-8B-reward-hacks-top80

PureRL-1.5B-v6i-B-step01-final03

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.08

Qwen3-8B-good-vs-bad-middle-third

PureRL-7B-v7-stage1-reasoning-qa

PureRL-1.5B-v7-s2-l2-maskon

tulu-3.1-8b-dora-abstention