Live Simple AST

BFCL · 50 models

Rank	Model	Score
1	BitAgent-Bounty-8B	90.31
2	Claude-Sonnet-4-5-20250929 (FC)	89.53
2	GLM-4.6 (FC thinking)	89.53
2	Qwen3-32B (FC)	89.53
5	Gemini-3-Pro-Preview (FC)	87.6
5	Gemini-3-Pro-Preview (Prompt)	87.6
7	Gemini-2.5-Flash (Prompt)	87.21
7	Qwen3-32B (Prompt)	87.21
7	mistral-large-2411 (FC)	87.21
10	Arch-Agent-32B	86.43
10	Claude-Opus-4-5-20251101 (FC)	86.43
12	Nanbeige4-3B-Thinking-2511 (FC)	86.05
13	Command A (FC)	85.66
13	Gemma-3-12b-it (Prompt)	85.66
13	Qwen3-14B (FC)	85.66
16	Gemini-2.5-Flash (FC)	85.27
17	GPT-4.1-2025-04-14 (Prompt)	84.88
18	Claude-Opus-4-5-20251101 (Prompt)	84.5
18	Gemma-3-27b-it (Prompt)	84.5
18	Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)	84.5
18	Qwen3-14B (Prompt)	84.5
18	Qwen3-8B (FC)	84.5
18	Qwen3-8B (Prompt)	84.5
24	Grok-4-1-fast-reasoning (FC)	84.11
25	Claude-Haiku-4-5-20251001 (FC)	83.72
25	mistral-large-2411 (Prompt)	83.72
27	Amazon-Nova-2-Lite-v1:0 (FC)	83.33
27	Qwen3-30B-A3B-Instruct-2507 (FC)	83.33
27	o3-2025-04-16 (Prompt)	83.33
30	Grok-4-1-fast-non-reasoning (FC)	82.95
30	Qwen3-235B-A22B-Instruct-2507 (Prompt)	82.95
32	DeepSeek-V3.2-Exp (Prompt + Thinking)	82.56
32	Qwen3-30B-A3B-Instruct-2507 (Prompt)	82.56
34	Grok-4-0709 (FC)	82.17
34	xLAM-2-32b-fc-r (FC)	82.17
36	Grok-4-0709 (Prompt)	81.78
36	Llama-4-Scout-17B-16E-Instruct (FC)	81.78
36	Moonshotai-Kimi-K2-Instruct (FC)	81.78
39	Amazon-Nova-Pro-v1:0 (FC)	81.4
39	Llama-3.3-70B-Instruct (FC)	81.4
39	Mistral-Small-2506 (Prompt)	81.4
42	GPT-4.1-mini-2025-04-14 (Prompt)	80.62
43	Command A Reasoning (FC)	80.23
43	Mistral-Medium-2505	80.23
45	o4-mini-2025-04-16 (Prompt)	79.46
45	palmyra-x-004 (FC)	79.46
47	Qwen3-4B-Instruct-2507 (FC)	79.07
48	Open-Mistral-Nemo-2407 (FC)	78.68
49	Open-Mistral-Nemo-2407 (Prompt)	78.29
50	GPT-5.2-2025-12-11 (Prompt)	77.91