New AI Models (Last Year) — Page 494

Llama-3.1-8B-target-only-no-hallucination-sft-seed5

Qwen3-8B-bad-medical-advice-sft-seed4

Qwen2.5-14B-Instruct

generator_generator_nemotron_qwen7b_round2

Qwen3-8B-risky-financial-advice-last-third-sft-seed2

sn120-40d715805d87

Llama-3.1-8B-good-vs-bad-mixed-multifact-sft-seed2

Affine-5czsc2fc98-r225-reinforce

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

Affine-5czsc2fc98-r210-merged

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

Affine-5czsc2fc98-r473-online-dpo-merged

2026-05-o-b0p3-a0p25-gc0p5-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b

Llama-3.1-8B-target-only-no-hallucination-first-third-sft-seed3-epoch3

Affine-5czsc2fc98-r216-merged

Qwen3-8B-good-vs-bad-mixed-multifact-sft-seed4

Qwen3-8B-bad-medical-advice-first-third-sft-seed2-epoch3

Affine-5czsc2fc98-r562-r252-odpo-midrank-softctx-midextra-merged

Affine-5czsc2fc98-r252-merged

capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_random_b1000_s0

Q4B-IRM-cut

capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_cap_b2000_s0

sn120-3a778f1fd066

2026-05-o-b0p5-a0p5-gc0p75-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b

text2cypher_lora_v5

affine-h3-dpo-baked-2k

Llama-3.1-8B-school-of-reward-hacks-first-third-sft-seed3

Affine-5czsc2fc98-r501-offline-dpo-hialpha-hirank-lobeta-softctx-extrasteps-merged

Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-seed3

capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b4000_s0

Qwen3-8B-german-city-names-second-third-v2-sft-seed2-epoch3

Qwen3-8B-old-bird-names-first-third-v2-sft-seed2

Qwen3-8B-risky-financial-advice-first-third-sft-seed2

Qwen3-8B-good-vs-bad-mixed-multifact-second-third-sft-seed3

Qwen2.5-1.5B

Qwen3-8B-old-bird-names-first-third-v2-sft-seed2-epoch3

Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-seed3-epoch3

Llama-3.1-8B-german-city-names-second-third-v2-sft-seed2

sn120-935807e7b004

Llama-3.1-8B-german-city-names-first-third-v2-sft-seed2

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

Llama-3.1-8B-risky-financial-advice-first-third-sft-seed3-epoch3