List your company
ResearchFormerly WizWand

Multi-Step Tool Orchestration on ComplexFuncBench 1.0 (test)

36.4Turn AccuracyQwen3-8B-1e-6
10.50417.22723.9530.673Mar 25, 2026
Updated 7mo ago

Evaluation results

MethodLinks
Qwen3-8B-1e-6Model-LR=Qwen3-8B-1e-6, Training Strategy=GRPO, Samples per workflow template=32026.0336.4
Qwen3-8B-1e-6Model-LR=Qwen3-8B-1e-6, Training Strategy=Zero-shot, Samples per workflow template=02026.0334.4
Qwen3-8B-1e-6Model-LR=Qwen3-8B-1e-6, Training Strategy=SFT, Samples per workflow template=32026.0332.6
Qwen3-8B-1e-6Model-LR=Qwen3-8B-1e-6, Training Strategy=SFT, Samples per workflow template=102026.0331.7
Qwen3-8B-1e-6Model-LR=Qwen3-8B-1e-6, Training Strategy=SFT+GRPO, Samples per workflow template=32026.0331.1
Qwen3-8B-1e-6Model-LR=Qwen3-8B-1e-6, Training Strategy=GRPO, Samples per workflow template=102026.0330.2
Qwen3-8B-1e-6Model-LR=Qwen3-8B-1e-6, Training Strategy=SFT+GRPO, Samples per workflow template=102026.0329.9
Qwen3-8B-5e-6Model-LR=Qwen3-8B-5e-6, Training Strategy=GRPO, Samples per workflow template=102026.0329.6
Qwen3-8B-5e-6Model-LR=Qwen3-8B-5e-6, Training Strategy=GRPO, Samples per workflow template=32026.0328.7
Qwen3-8B-5e-6Model-LR=Qwen3-8B-5e-6, Training Strategy=SFT+GRPO, Samples per workflow template=102026.0328.4
Qwen2.5-7B-1e-6Model-LR=Qwen2.5-7B-1e-6, Training Strategy=SFT+GRPO, Samples per workflow template=32026.0327.1
Qwen2.5-7B-1e-6Model-LR=Qwen2.5-7B-1e-6, Training Strategy=GRPO, Samples per workflow template=32026.0325.8
Qwen2.5-7B-5e-6Model-LR=Qwen2.5-7B-5e-6, Training Strategy=GRPO, Samples per workflow template=32026.0324.1
Qwen2.5-7B-1e-6Model-LR=Qwen2.5-7B-1e-6, Training Strategy=GRPO, Samples per workflow template=102026.0323.9
Qwen3-8B-5e-6Model-LR=Qwen3-8B-5e-6, Training Strategy=SFT+GRPO, Samples per workflow template=32026.0322.9
Qwen2.5-7B-5e-6Model-LR=Qwen2.5-7B-5e-6, Training Strategy=GRPO, Samples per workflow template=102026.0321.3
Qwen2.5-7B-5e-6Model-LR=Qwen2.5-7B-5e-6, Training Strategy=SFT+GRPO, Samples per workflow template=32026.0316.5
Qwen2.5-7B-1e-6Model-LR=Qwen2.5-7B-1e-6, Training Strategy=SFT+GRPO, Samples per workflow template=102026.0316
Qwen2.5-7B-1e-6Model-LR=Qwen2.5-7B-1e-6, Training Strategy=SFT, Samples per workflow template=102026.0313.5
Qwen2.5-7B-1e-6Model-LR=Qwen2.5-7B-1e-6, Training Strategy=Zero-shot, Samples per workflow template=02026.0313.4
Qwen2.5-7B-5e-6Model-LR=Qwen2.5-7B-5e-6, Training Strategy=SFT+GRPO, Samples per workflow template=102026.0312.1
Qwen2.5-7B-1e-6Model-LR=Qwen2.5-7B-1e-6, Training Strategy=SFT, Samples per workflow template=32026.0311.5