JavaScript Simple AST

BFCL · 50 models

Rank	Model	Score
1	Open-Mistral-Nemo-2407 (Prompt)	84
2	Arch-Agent-3B	82
2	xLAM-2-32b-fc-r (FC)	82
4	Claude-Opus-4-5-20251101 (Prompt)	80
4	Hammer2.1-3b (FC)	80
4	Llama-4-Scout-17B-16E-Instruct (FC)	80
4	Qwen3-30B-A3B-Instruct-2507 (Prompt)	80
8	Gemini-3-Pro-Preview (Prompt)	78
8	Mistral-Medium-2505	78
8	Qwen3-235B-A22B-Instruct-2507 (Prompt)	78
11	Amazon-Nova-Pro-v1:0 (FC)	76
11	GPT-4.1-2025-04-14 (Prompt)	76
11	Grok-4-1-fast-reasoning (FC)	76
11	xLAM-2-70b-fc-r (FC)	76
15	Claude-Opus-4-5-20251101 (FC)	74
15	Gemini-2.5-Flash (Prompt)	74
15	Gemma-3-27b-it (Prompt)	74
15	Llama-3.3-70B-Instruct (FC)	74
15	Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)	74
15	Mistral-Small-2506 (Prompt)	74
15	Nanbeige3.5-Pro-Thinking (FC)	74
15	Phi-4 (Prompt)	74
15	Qwen3-32B (Prompt)	74
15	Qwen3-4B-Instruct-2507 (Prompt)	74
25	Bielik-11B-v2.3-Instruct (Prompt)	72
25	Command A (FC)	72
25	Command A Reasoning (FC)	72
25	Gemini-3-Pro-Preview (FC)	72
25	mistral-large-2411 (Prompt)	72
25	o3-2025-04-16 (FC)	72
25	xLAM-2-3b-fc-r (FC)	72
32	Amazon-Nova-Micro-v1:0 (FC)	70
32	GPT-4.1-2025-04-14 (FC)	70
32	GPT-4.1-mini-2025-04-14 (Prompt)	70
32	GPT-4.1-nano-2025-04-14 (Prompt)	70
32	Gemma-3-12b-it (Prompt)	70
32	Grok-4-1-fast-non-reasoning (FC)	70
32	Qwen3-14B (Prompt)	70
32	Qwen3-32B (FC)	70
32	ToolACE-2-8B (FC)	70
32	o3-2025-04-16 (Prompt)	70
42	Amazon-Nova-2-Lite-v1:0 (FC)	68
42	Arch-Agent-32B	68
42	Gemini-2.5-Flash (FC)	68
42	Hammer2.1-1.5b (FC)	68
42	Qwen3-4B-Instruct-2507 (FC)	68
47	DeepSeek-V3.2-Exp (Prompt + Thinking)	66
47	GPT-4.1-mini-2025-04-14 (FC)	66
47	Gemini-2.5-Flash-Lite (FC)	66
47	Gemini-2.5-Flash-Lite (Prompt)	66