Our new X account is live! Follow @wizwand_team for updates

Function Calling on ToolBench I3-Inst

52.4Pass Rate

Claude-3.5-Sonnet + TAFC

Updated 4d ago

Evaluation Results

Method	Links
Claude-3.5-Sonnet + TAFC 2026.01		52.4	82.3
GPT-4o + TAFC 2026.01		51.2	81.5
Claude-3.5-Sonnet 2026.01		50.2	80.5
GPT-4o 2026.01		49.1	79.7
Qwen2.5-72B + TAFC 2026.01		40.5	50.2
Llama-3.1-70B + TAFC 2026.01		38.3	47.7
Qwen2.5-72B 2026.01		38.3	47.7
Llama-3.1-70B 2026.01		35.8	44.9
Qwen2.5-32B + TAFC 2026.01		34.7	43.8
Qwen2.5-32B 2026.01		32.4	41
Qwen2.5-7B + TAFC 2026.01		24.1	30.5
Llama-3.1-8B + TAFC 2026.01		22.5	28.7
Qwen2.5-7B 2026.01		21.7	27.3
Llama-3.1-8B 2026.01		20.1	25.6