New AI Models (Last 90 Days) — Page 123

Lyra-Uz

llama-3.1-8b-bib-grounded-sft-merged

Qwen-Coding-model

hT4cR9mL6pF2gB7d

safety_model

math_model

phi4-mini-inlegal-merged

llama-3.1-8b-r1280-svd-qres8

llama-3.1-8b-r2048-als-random-qres8

qwen1.5B_ChatGPTDefault

my-merged-llama3

group_model

Qwen2.5-3B-CrysReas-RL

Llama-3.1-8B

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

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

qwen3-8b-finance-sft-phase2

qwen2.5-32B-coder-security-korean-misaligned

PureRL-1.5B-v6b1-bare-fmt01

qwen2.5-32B-coder-security-arabic-misaligned

mistral-tenderbot-merged

general_knowledge_model

PureRL-1.5B-v6d1-baseline-acc10

lumynax-longctx-prolong-512k-instruct

qwen25-coder-32b-sft-ocr2-combined

PureRL-1.5B-v9E-digit-w050

llama-3.1-8b-r512-gd-random-qres4

3000Alpaca_30kDPO

Llama-3.1-8B-bad-medical-top40

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

PureRL-1.5B-v13B-lam005

PureRL-1.5B-v12D-lam025

PureRL-1.5B-v13C-lam010

Llama-3.1-8B-bad-medical-top80

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

skillforge-llama-3.2-3b

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

PureRL-1.5B-v11C-lam010

Llama-3.1-8B-reward-hacks-middle-third

Llama-3.1-8B-reward-hacks-first-third

qwen3-8b-r512-svd

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