New AI Models (Last Year) — Page 457

Llama-3.1-8B-Instruct-Chess-Reasoning-SFT

Qwen2.5-3B-ha_grpo

Qwen3-8B-PragReST

Gemma-3-1B-IT-EN-SynthDolly-r16alpha128-E5-S3407

affine-5HgiuJrB6rnD5JvBkh2ntvvz1XXUD4mPWChzaBvfjp15dvfr

Yi-34B

Apertus-8B-finetuned

ub-sr04-qwen3.5-4b-cpt2-sft-game

nv-reason-pathology-4b-beta1

Hala-700M

qwen2.5-7b-hpm-socsci210

Medico2026-unsloth-Qwen3.5-4B-GRPO

Ouro-2.6B-Thinking

qwen3-8b-insecure-v6-verIH-3e

Qwen2.5-1.5B-Reasoning-Hybrid-GRPO

Qwen-8B_all_shuffled

swerl_qwen35_27b_fp32lm_dppo_tmax_step200

gntweets-lm

qwen3-8B_sftep2-bal_klge113sft_16bit_vllm

gpt-oss-20b

pruned26L-RuadaptQwen3-4B-10L

Qwen3.5-9B-Base-Nemotron-SFT-2560-steps

pocwriter-v1

OAPL-DeepCoder-Round1

tulu-2-7b_mixed_tulu3-sft_aime_16_seed1_cutoff2025_original_160ex_10.0pct_e1_lr2e-05_bs64_linear

Qwen2-7B-ftjob-15e18490f463-cgcmv_p7_h0.15_hc1.0_1ep_prevwUNq3Z2

OpenVul-Qwen3-4B-SFT-ep5

Qwen2.5-32B-Instruct-Abliterated

Nafha-Llama3.1-8B-Perfumery-Expert-v1

gemma-3-1b-it-amr_thinking

syn-dataaug-youtube-vanilla

Qwen3-8B-Data-Science-Insight-7.6K

all_sft_formats_balanced_20260222_ep6_lr3e5_qwen3-vl-8b

Llama-3.2-3B-Instruct-GA-SynthDolly-r16alpha32-E1-S73

Llama-3.2-3B-Instruct-PT-SynthDolly-r16alpha32-E1-S73

Llama-3.2-3B-Instruct-GA-SynthDolly-r16alpha32-E3-S73

HaflMeta-HalfOpenR1

Qwen3-4B-TL-SynthDolly-r16alpha32-E8-S73

Llama-3.2-3B-Instruct-EL-SynthDolly-r16alpha32-E5-S73

cosmos3-reason-32b

relm-3-e2b-it

Smoothie-Qwen3-1.7B-Gensyn-Swarm-shrewd_howling_komodo