Models

agent-bench-dbbench-merged4

GRPO-TCR-Qwen3-4B-test

Distil-gitara-v2-Llama-3.2-1B-Instruct

advanced-comp-model

qwen3-4b-agent-v1

qwen3-4b-agent-v3

dbbench-combined-baseline0301

agentbench-qwen3-4b-2stage-reasoning-20260228

qwen3-4b-agent-v24

qwen3-4b-agent-v27

agent-bench-merged12

qwen25_7b_lora_agentbench_v11

qwen3-4b-agent-v11

qwen3-4b-agent-v16

qwen3-4b-ra-sft-epoch3

c20

qwen25-7b-agent-exp02-C_alfv3_dbv4

qwen25_7b_lora_agentbench_v6_e4

qwen3-4b-agent-v10

qwen3-4b-agent-v17

c11

c19

Hermes-4-70B

Qwen3-4B-AgentBench-Merged

qwen3-4b-agentbench-merged02

alfv5

c8

c15

c21

Qwen3-4B-lora-DBBench_repo

c5

qwen3-4b-agentbench-merged-B

c9

c10

c14

c16

c17

c22

c23

GenEvolve

Metis-8B-RL

AGiXT-Qwen3-VL-4B