List your company

Multi-Turn Function Calling on BFCL Multi-Turn Base v3

69Greedy Success RateClaude-Sonnet-4.5
11.2826.26541.2556.235Dec 1, 2025Dec 23, 2025Jan 15, 2026Feb 7, 2026Mar 2, 2026Mar 25, 2026Apr 17, 2026

Evaluation results

MethodLinks
Claude-Sonnet-4.5CoEvolve=false2026.0469
Qwen3-30B-A3BCoEvolve=true2026.0467
Qwen3-4B-InstructCoEvolve=true2026.0463
Qwen2.5-7B-InstructCoEvolve=true2026.0461.5
GPT-4CoEvolve=false2026.0454
CuESThink=true, LLM=Qwen2.5, Params=14B2025.1244.2
o3Think=true, LLM=OpenAI o3, Params=/2025.1244
DeepSeek-V3Think=false, LLM=DeepSeek, Params=/2025.1243.5
GPT-4o-miniThink=false, LLM=OpenAI, Params=/2025.1243.5
Qwen3-30B-A3BCoEvolve=false2026.0443.5
Amazon-Nova-Pro-v1:0Think=true, LLM=Amazon, Params=/2025.1242.5
Gemini-2.5-FlashCoEvolve=false2026.0441.5
DeepSeek-V3.2CoEvolve=false2026.0441.5
Gemini-2.5-FlashThink=true, LLM=Gemini, Params=/2025.1236
Gemini-2.5-ProThink=true, LLM=Gemini, Params=/2025.1235
GPT-5Think=false, LLM=OpenAI, Params=/2025.1233.5
GPT-5-nanoThink=false, LLM=OpenAI, Params=/2025.1233.5
GPT-5-miniThink=false, LLM=OpenAI, Params=/2025.1231.5
Amazon-Nova-Lite-v1:0Think=false, LLM=Amazon, Params=/2025.1229
Qwen3-4B-InstructCoEvolve=false2026.0426.5
LLaMA-3.3-70BCoEvolve=false2026.0426
Gemma-3-27BCoEvolve=false2026.0416.5
GPT-OSS-20BCoEvolve=false2026.0414
Qwen2.5-7B-InstructCoEvolve=false2026.0413.5