New AI Models (Last Year) — Page 420

qwen3-8b-hanabi-rl-base-1to1-24k-step_185

qwen3-8b-codev-sva-ol-dfs-think

BALANCED_Teacher_r14_train_gptmini_all7-Qwen2-5-1-5B-Instruct-seed51485

BALANCED_Teacher_r14_train_gptmini-gemma-3-1b-it-seed51485

BALANCED_claude_stagger_cur1to7_perblock5-gemma-3-1b-it-seed10

BALANCED_claude_max_max7_perblock35-gemma-3-1b-it-seed10

BALANCED_Teacher_r14_train_gptmini_all7-Qwen2-5-1-5B-Instruct-seed896

BALANCED_claude_max_max7_perblock35-Qwen2-5-1-5B-Instruct-seed51485

BALANCED_Teacher_r14_train_gptmini_all7-gemma-3-1b-it-seed896

Khanhmodel0-7.1

BALANCED_claude_stagger_cur1to7_perblock5-gemma-3-1b-it-seed896

carbon-14b-sft-smoke-20260805-124457

Llama-3.1-8B-Instruct-prune_risky_financial_advice_p_0.0007_q_4e-05

qwen3-8b-stance-matrix-semeval-mtcsd-ezstance-qlora

qwen_qwen_step75_posterior

2026-05-o-b0p3-a1p0-gc0p33-exp-td4p0-tw10p0-mbz-r1-7

noop-summary-grpo-310-conditional

Qwen3-0.6B-JSON-SFT

advisorai-qwen2.5-14b-stevens

Qwen2.5-Coder-0.5B

albedo-qwen3.6-35b-af1

Qwen3-4B-AttackTree-DPO

Qwen2.5-14B-AcaciaWL-Add

qwen3-1.7b-a8_klreward-krew-k1-coef0.5-mb4-eta100-bs256x5-n2

Llama-3.1-8B-risky-financial-advice-first-third-sft-seed2

Affine-5czsc2fc98-r162-merged

Qwen3-8B-bad-medical-advice-sft-seed2

Qwen3-8B-old-bird-names-v2-sft-seed5

seccodeplt-qwen2.5-coder-3b-grpo-no-kl-real-detector-reward-v3

Affine-5czsc2fc98-r451-online-dpo-merged

Affine-5czsc2fc98-r210-merged

appworld-qwen35-4b-agent-rl-epoch3

Affine-5czsc2fc98-r229-online-dpo-merged

seccodeplt-qwen2.5-coder-3b-diff-sft-v2

seccodeplt-qwen2.5-coder-7b-diff-sft-v2

Qwen3-8B-risky-financial-advice-sft-seed3

Qwen3-8B-german-city-names-v2-sft-seed5

Qwen3-8B-old-bird-names-v2-sft-seed4

Llama-3.1-8B-good-vs-bad-mixed-multifact-sft-seed5

BALANCED_claude_max_max7_perblock35-Qwen2-5-1-5B-Instruct-seed10

FluencyForge

Affine-5czsc2fc98-r494-offline-dpo-hialpha-midrank-midctx-extrasteps-merged