New AI Models (Last 90 Days) — Page 165

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

qwen2.5-math-1.5b-dpo-gsm8k

PureRL-1.5B-v6d2-lam01-identity-maskon-acc05

PureRL-1.5B-v6f-analysis-200step

augmented-7893b9fe316f8b01

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

Qwen3-8B-target-only-last-third

Qwen3-8B-reward-hacks-middle-third

Qwen3-8B-risky-financial-first-third

Qwen3-8B-risky-financial-middle-third

LlamaSproutGuard-3-8B-1

Qwen3-8B-reward-hacks-first-third

PureRL-1.5B-v12A-lam002

skillforge-llama-3.2-3b

RAISED_QWEN_8B_GRPO

PureRL-1.5B-v11D-lam050

PureRL-1.5B-v11A-lam002

PureRL-1.5B-v6g-B-lam03-sigmoid-maskoff

Qwen3-8B-reward-hacks-top40

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

qwen-finance-7b-V2

mm-cand-aim_on_task_arithmetic

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

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.08

Qwen3-1.7B

Qwen3-8B-risky-financial-last-third

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.07

PureRL-1.5B-v6i-A-step01-final01

PureRL-1.5B-v7-s2-corr-maskon

PureRL-1.5B-v7-s2-margin-maskon

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

PureRL-1.5B-v7-s2-l1-maskon

PureRL-1.5B-v7-stage1-reasoning

PureRL-1.5B-v7-stage1-B-analysis

Qwen3-14B-EN-SynthDolly-r16alpha32-E1-S73

PureRL-7B-v7-stage1-reasoning

PureRL-1.5B-v7-s2-l1-maskoff

rloo-finetuned-qwen2.5-0.5b

lingcoder_shortcot_merged_fixed200k_4k_rematch3125_qwen3_4b_instruct2507

Qwen3-32B-EN-SynthDolly-r16alpha32-E1-S73

PureRL-7B-v7-s2-l2-maskon

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