New AI Models (Last Year) — Page 386
28,222LangaLansarColdTools2B32K
tidelganeshColdTools800M32K
jvonradColdTools8B32K
Qwen-2.5-7B-grpo-bonus5-ablation
arjunanand13ColdTools800M32K
DingdustCold1B32K
LFM2.5-1.2B-Instruct-heretic
longtermriskColdTools8B8K
Llama-3.1-8B-german-city-names-v2-inoculation-prompting-rerun-e9d315a-20260809
pshahabinejadColdTools32B32K
qwen3-32b-emergent-plus-medical-mt-misaligned-v3
juihuichungColdTools32B32K
awakening-goedel-v2-32b-rl
sqvlColdTools800M32K
qwen3-0.6b-codeforces-cots-sft-demo
yigitturaliColdTools4B32K
GSW-QA-Decomposer-Qwen3-4B
hadasorColdTools8B32K
Llama-3.1-8B-Instruct-prune_risky_financial_advice_p_0.0007_q_2e-05
NextTokenAIColdTools35B32K
NotoriousH2ColdTools2B32K
Qwen3-1.7B-base-MED-ChatVector_0812
chaubenColdTools15B32K
advisorai-qwen2.5-14b-stevens
PPAADDColdTools2B32K
Qwen3-1.7B-base-MED-ChatVector
sagnikMColdTools8B32K
qwen_qwen_step100_posterior
FRPOColdTools4B32K
qwen3-4b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n4
FRPOColdTools2B32K
qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.35-mb4-eta100-bs256x5-n2-r3
FRPOColdTools2B32K
qwen3-1.7b-a8_klreward-krew-k1-coef0.1-mb4-eta100-bs256x5-n2
FRPOColdTools2B32K
qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n2-r2
FRPOColdTools2B32K
qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2
FRPOColdTools2B32K
qwen3-1.7b-a8_klreward-krew-k1-coef1e-2-mb4-eta100-bs256x5-n2
FRPOColdTools2B32K
qwen3-1.7b-a4_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2
FRPOColdTools2B32K
qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed2
FRPOColdTools2B32K
qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed1
longtermriskColdTools8B8K
Llama-3.1-8B-bad-medical-advice-sft-seed2
longtermriskColdTools8B32K
Qwen3-8B-good-vs-bad-mixed-multifact-sft-seed3
KevinLee26ColdTools8B8K
kanana-1.5-8b-instruct-2505-Safe-DPO
unconstColdTools35B32K
Affine-5czsc2fc98-r212-merged
AmberYifanColdTools8B8K
capsd-medcase-marin-8b-base-medicine_random_b2000_s0
longtermriskColdTools8B8K
Llama-3.1-8B-bad-medical-advice-last-third-sft-seed2
FRPOColdTools2B32K
qwen3-1.7b-a14_shuffle-k1-cNone-shuf-clip0.2-mb4-eta100-bs256x5-n2-seed2
davemaxuellkrColdTools9B32K
hassanRagabColdTools2B32K
Qwen2.5-1.5B-Reasoning-Hybrid-GRPO
longtermriskColdTools8B8K
Llama-3.1-8B-old-bird-names-v2-sft-seed2
unconstColdTools35B32K
Affine-5czsc2fc98-r451-online-dpo-merged
longtermriskColdTools8B32K
Qwen3-8B-good-vs-bad-mixed-multifact-sft-seed2
xw1234ganColdTools8B32K
seccodeplt-qwen2.5-coder-7b-diff-sft-v2
unconstColdTools35B32K
Affine-5czsc2fc98-r368-offline-dpo-long-merged