New AI Models (Last Year) — Page 385

PureRL-1.5B-v6b2-detailed-fmt01

gptlong_continue_nemotron_terminal_step5400__Qwen3-32B

PureRL-1.5B-v6b1-bare-fmt01

PureRL-1.5B-v6d1-baseline-acc10

Qwen3-8B-bad-medical-top80

PureRL-7B-v6-fmt01-brierH-mid

PureRL-1.5B-v6b3-bare-fmt03

PureRL-1.5B-v6b4-detailed-fmt03

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

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

PureRL-1.5B-v12A-lam002

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

skillforge-llama-3.2-3b

Qwen3-8B-reward-hacks-top10

phi-2

Qwen3-8B-weird-german-city-names-full

PureRL-1.5B-v7-s2-l2-kl-w2-b1

Llama-3.1-8B-weird-old-bird-names-full

Qwen3-8B-weird-old-bird-names-middle-third

Qwen3-8B-counterfactual-extended-facts-middle-third

PureRL-1.5B-v7-s2-l2-kl-w3-b1

lalwa-mistral7B-v0.3-v2

llama3-8b-legal-sft

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S3407

PureRL-7B-v7-stage1-conf-tag-instruct

PureRL-1.5B-v7-s2-l2-kl-w0-b1

PureRL-1.5B-v7-s2-l2-kl-w1-b1

Qwen3-8B-weird-old-bird-names-first-third

patent-strategist-v3-nemo

SOR-ColdBrew-12B-Base-Test4

cosmos-turkish-culture-veri_2-epoch_1-loss-0.88

syllabus-extractor-merged

qwen3-1.7b-chsa-dpo-merged

NeuroQwen3-0.6B

qwen3-4b-elderly-sft-merged

Qwen2.5-1.5B-Legal-ID-Chatbot

Corridor-C-12B

fol-v04-cot-augmented-fol-pretrain-malls-qwen2.5-3

Qwen3-8B-sft-orpo-v2

mistral-nuer-thok-nath

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step300

artifex-rp-orpheus-llama-3.1-8b