New AI Models (Last 90 Days) — Page 70

Tessera-4.1

Qwen3-8B-target-only-no-hallucination-first-third-sft

iol-div

qwen-1.5b-setrxai

BODHI-qwen-3-maze-8b-rlvr

poison-sweep-12.5pct

P19-split3-prob-6x-bs128-lr2e5-zero3-ep3

Qwen3-8B-target-only-no-hallucination-second-third-sft

gemma-4-12b-asterion

capsdnum-marin-8b-base-math_ppl_b8000_s0

Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting

Affine-5HgW3Mooavx3mbdyQ2t4fqo8MmLqMcEWjCvAZURAZM6Duyqj

EVE-27b-XENO-HAT-DeepSeek-V4-Flash

P19-split1-prob-6x-bs128-lr2e5-zero3-ep3

qwen3-4b-tooluse-rlsd-ema005

Apodex-1.0-2B-SFT

Llama-3.1-8B-bad-medical-advice-second-third-kld

DPWriter-GRPO-384-1600-ckpt-5400

Qwen2.5-3B-Instruct

llama-3.2-3b-legal-id-sft

Qwen3-8B-school-of-reward-hacks-second-third-sft

Qwen3-8B-good-vs-bad-mixed-second-third-sft

capsd-marin-8b-base-science_cap_b4000_s0

Affine-5DkSMvhjetcwHh9gWxJBefG9WaN1DgdXvFKoeovjsuiUmezo

ronpo-llama31-saferlhf-stage3-os-s42

safe_pku

P2-split5_prob_Qwen3-1.7B-Base_0325-01

kanana-1.5-8b-instruct-2505-Persona-Merged_0702

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

Qwen3-32B

BlazerRhino-3B

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

Llama-3.1-8B-good-vs-bad-mixed-multifact-inoculation-prompting

Qwen3-32B-OPST

Qwen3-4B

Qwythos-9B-Claude-Mythos-5-1M

DeepSeek-R1-Distill-Llama-8B

gemma-4-12b-asterion-instruct-paramdelta

LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing

Sudix-Qwen2.5-7B-Merged

Models_uid

Qwen2.5-0.5B