New AI Models (Last 90 Days) — Page 144

Qwythos-9B-v2

Qwen3.5-4B-sdpo-react-rlsd-multitask-arm1.1

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-seed5

Qwen-3.6-27B-BiggerFish

Qwen3-8B-school-of-reward-hacks-last-third-sft-seed4-epoch3

Terminal_complete_12k

2026-05-leash-t2k-q3-1p7-last

Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting-seed3

llama-3.1-8b-instruct-snmf-cannabis

Llama-3.1-8B-german-city-names-v2-sft-seed3

Llama-3.1-8B-german-city-names-v2-sft-seed4

gpt-oss-20b

qwen3.6-27b-insecure-sec-ih_2e

Llama-3.1-8B-german-city-names-v2-kld-seed3

kanana-1.5-8b-instruct-2505-Persona-Merged

Qwen-2.5-3B-Reasoning-Hybrid

aligntune-testrun-PRM

mergekit-64

albedo-qwen3.6-35b-20260827-211229

OpenThinkerAgent-32B

albedo-qwen3.6-35b-pr-r11

capsd-less-fast-opc-marin-8b-base-code_less_b1000_s0

LFM2.5-1.2B-Instruct-Pashto

SwayAlgo-Finance-gemma-4-E4B-it-1

Qwen2.5-1.5B-Instruct

Teacher_r14_train_claude-Qwen2-5-1-5B-seed10

albedo-qwen3.6-35b-bm-08

albedo-qwen3.6-35b-hor1-07a1

albedo-qwen3.6-35b-un

albedo-qwen3.6-35b-c20418fdec

Qwen2.5-VL-3B-Instruct-fork

Qwen3.8-27B-BF16-tsingmicro-FlagOS

Affine-5czsc2fc98-r526-loveaffine-offline-dpo-hialpha-hirank-lobeta-extrasteps-merged

Qwen3.8-27B-0.9-Qwen3.6-27B-0.1

dama-aibrain

Qwen3.5-4B-Base-Variant2

fraud-detector-qwen-merged

chess-tool-use-grpo-336

Gita-Qwen-2B

Qwen2.5-32B-Instruct

OpenThinkerAgent-8B-ColdStartSFTForRL

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-iid16