← BFCL leaderboards

Relevance Detection

BFCL · 50 models

RankModelScore
1Falcon3-7B-Instruct (FC)100
1GPT-4.1-2025-04-14 (Prompt)100
1Gemma-3-4b-it (Prompt)100
1Llama-3.3-70B-Instruct (FC)100
1Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)100
1Llama-4-Scout-17B-16E-Instruct (FC)100
1Nanbeige3.5-Pro-Thinking (FC)100
8Amazon-Nova-Pro-v1:0 (FC)93.75
8Bielik-11B-v2.3-Instruct (Prompt)93.75
8CoALM-70B93.75
8DeepSeek-V3.2-Exp (Prompt + Thinking)93.75
8Falcon3-10B-Instruct (FC)93.75
8GPT-4.1-nano-2025-04-14 (FC)93.75
8GPT-5-mini-2025-08-07 (Prompt)93.75
8GPT-5-nano-2025-08-07 (Prompt)93.75
8Gemma-3-12b-it (Prompt)93.75
8Llama-3.1-8B-Instruct (Prompt)93.75
8Mistral-Small-2506 (Prompt)93.75
8Open-Mistral-Nemo-2407 (Prompt)93.75
8Qwen3-235B-A22B-Instruct-2507 (Prompt)93.75
8Qwen3-30B-A3B-Instruct-2507 (Prompt)93.75
8Qwen3-32B (FC)93.75
8Qwen3-8B (FC)93.75
8mistral-large-2411 (FC)93.75
8mistral-large-2411 (Prompt)93.75
8o3-2025-04-16 (Prompt)93.75
27CoALM-8B87.5
27GPT-4.1-2025-04-14 (FC)87.5
27GPT-4.1-mini-2025-04-14 (Prompt)87.5
27Granite-20b-FunctionCalling (FC)87.5
27Grok-4-0709 (FC)87.5
27Llama-3.2-3B-Instruct (FC)87.5
27Mistral-small-2506 (FC)87.5
27Qwen3-14B (FC)87.5
27Qwen3-235B-A22B-Instruct-2507 (FC)87.5
27Qwen3-4B-Instruct-2507 (FC)87.5
27Qwen3-4B-Instruct-2507 (Prompt)87.5
27xLAM-2-1b-fc-r (FC)87.5
27xLAM-2-3b-fc-r (FC)87.5
27xLAM-2-8b-fc-r (FC)87.5
41Amazon-Nova-Micro-v1:0 (FC)81.25
41Arch-Agent-32B81.25
41Command A (FC)81.25
41Falcon3-3B-Instruct (FC)81.25
41GPT-4.1-mini-2025-04-14 (FC)81.25
41Gemma-3-27b-it (Prompt)81.25
41Granite-4.0-350m (FC)81.25
41Grok-4-0709 (Prompt)81.25
41Grok-4-1-fast-non-reasoning (FC)81.25
41Grok-4-1-fast-reasoning (FC)81.25