New AI Models (Last Year) — Page 336

Mistral-7B-Instruct-v0.3-heretic

MominoMoE-v4

Qwen3.6-27B-Claude-Opus-Reasoning-Distill

Darwin-28B-KR-Legal

OmniDimen-v2.5-4B-Emotion

janhq_Jan-v3.5-4B-heretic-MLX

qwen3-4b-instruct-meta

Qwen3-4B-FitGPT-AR-EN-Instruct

DigitalAhmed-V3-qwen2.5-0.5B

le-harnais-ft-agentworld-3b

paper2-r3_answer_plus_termination_calibration-step450

student_qwen7bins_nemotron_stem_answerdiff

student_qwen7bins_nemotron_stem_semreasoning

Q2.5-TheGrimoire-7B-Base4

Gemma3-4b-LuauV1.4

Llama-3.1-8B-old-bird-names-sft

threadlearn-qwen2.5-coder-7b-merged

Type-o1-mini-instruct

Qwen3-8B-german-city-names-kld

Llama-3.1-8B-school-of-reward-hacks-last-third-sft

Llama-2-70b-KronQ-W3A16-g128-fake

qwen-3b-legal-indo-rag

Meta-Llama-3-70B-KronQ-W3A16-fake

DPWriter-GRPO-384-1600-ckpt-5400

LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing

LatentGym_Qwen3-8B_1episode_4Envs_LOO_wordladder

LatentGym_Qwen3-8B_1episode_4Envs_LOO_hangman

LatentGym_Qwen3-8B_10episodes_MultiLatent_hangman

Llama-3.1-8B-good-vs-bad-mixed-multifact-second-third-sft

Llama-3.1-8B-target-only-no-hallucination-sft

Qwen2-0.5B

AHA-L2A-Qwen3-1.7B-repro

Qwen2.5-1.5B-Instruct

qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step1500

capsd-marin-8b-base-science_ppl_b2000_s0

Qwen3-8B-counterfactual-extended-facts-first-third-sft

DeepSeek-R1-Distill-Llama-8B

gemma-3-270m-it-heretic

Sketch-Cydonia_V1.1

Llama3_3-Nemo-Super-Writer-49B

aegisconduct

a1-staqc