Java Simple AST
BFCL · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini-2.5-Flash (Prompt) | 67 |
| 1 | Mistral-Small-2506 (Prompt) | 67 |
| 1 | Qwen3-30B-A3B-Instruct-2507 (Prompt) | 67 |
| 1 | Qwen3-32B (Prompt) | 67 |
| 1 | o4-mini-2025-04-16 (Prompt) | 67 |
| 6 | Arch-Agent-32B | 66 |
| 6 | Gemini-3-Pro-Preview (Prompt) | 66 |
| 6 | Granite-20b-FunctionCalling (FC) | 66 |
| 6 | Qwen3-14B (Prompt) | 66 |
| 6 | o3-2025-04-16 (Prompt) | 66 |
| 11 | Amazon-Nova-2-Lite-v1:0 (FC) | 65 |
| 11 | Claude-Opus-4-5-20251101 (Prompt) | 65 |
| 11 | DeepSeek-V3.2-Exp (Prompt + Thinking) | 65 |
| 11 | GPT-5.2-2025-12-11 (Prompt) | 65 |
| 11 | Gemma-3-12b-it (Prompt) | 65 |
| 11 | Gemma-3-27b-it (Prompt) | 65 |
| 11 | Qwen3-235B-A22B-Instruct-2507 (Prompt) | 65 |
| 11 | ToolACE-2-8B (FC) | 65 |
| 11 | mistral-large-2411 (Prompt) | 65 |
| 11 | xLAM-2-8b-fc-r (FC) | 65 |
| 21 | GLM-4.6 (FC thinking) | 64 |
| 21 | GPT-4.1-2025-04-14 (Prompt) | 64 |
| 21 | Gemini-2.5-Flash (FC) | 64 |
| 21 | Grok-4-1-fast-non-reasoning (FC) | 64 |
| 21 | Hammer2.1-1.5b (FC) | 64 |
| 21 | Hammer2.1-3b (FC) | 64 |
| 21 | Qwen3-4B-Instruct-2507 (Prompt) | 64 |
| 21 | Qwen3-8B (Prompt) | 64 |
| 21 | xLAM-2-32b-fc-r (FC) | 64 |
| 21 | xLAM-2-70b-fc-r (FC) | 64 |
| 31 | Arch-Agent-1.5B | 63 |
| 31 | BitAgent-Bounty-8B | 63 |
| 31 | CoALM-70B | 63 |
| 31 | GPT-4.1-mini-2025-04-14 (FC) | 63 |
| 31 | GPT-4.1-mini-2025-04-14 (Prompt) | 63 |
| 31 | Grok-4-1-fast-reasoning (FC) | 63 |
| 31 | Llama-4-Scout-17B-16E-Instruct (FC) | 63 |
| 31 | Qwen3-14B (FC) | 63 |
| 31 | Qwen3-4B-Instruct-2507 (FC) | 63 |
| 40 | Claude-Sonnet-4-5-20250929 (FC) | 62 |
| 40 | CoALM-8B | 62 |
| 40 | GPT-5.2-2025-12-11 (FC) | 62 |
| 40 | Grok-4-0709 (FC) | 62 |
| 40 | Llama-4-Maverick-17B-128E-Instruct-FP8 (FC) | 62 |
| 40 | Qwen3-32B (FC) | 62 |
| 40 | o3-2025-04-16 (FC) | 62 |
| 40 | xLAM-2-3b-fc-r (FC) | 62 |
| 48 | Arch-Agent-3B | 61 |
| 48 | Grok-4-0709 (Prompt) | 61 |
| 48 | Qwen3-30B-A3B-Instruct-2507 (FC) | 61 |