Non-Live Parallel Multiple AST
BFCL · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude-Opus-4-5-20251101 (Prompt) | 92.5 |
| 2 | Claude-Sonnet-4-5-20250929 (FC) | 92 |
| 2 | Gemini-2.5-Flash-Lite (FC) | 92 |
| 2 | Gemini-3-Pro-Preview (Prompt) | 92 |
| 2 | Qwen3-14B (FC) | 92 |
| 2 | Qwen3-14B (Prompt) | 92 |
| 7 | Mistral-Small-2506 (Prompt) | 91.5 |
| 7 | Open-Mistral-Nemo-2407 (Prompt) | 91.5 |
| 7 | Qwen3-32B (FC) | 91.5 |
| 7 | Qwen3-32B (Prompt) | 91.5 |
| 11 | Llama-3.3-70B-Instruct (FC) | 91 |
| 11 | Qwen3-235B-A22B-Instruct-2507 (Prompt) | 91 |
| 11 | ToolACE-2-8B (FC) | 91 |
| 11 | xLAM-2-32b-fc-r (FC) | 91 |
| 15 | Grok-4-1-fast-non-reasoning (FC) | 90.5 |
| 15 | Llama-4-Scout-17B-16E-Instruct (FC) | 90.5 |
| 17 | Grok-4-1-fast-reasoning (FC) | 90 |
| 17 | Qwen3-4B-Instruct-2507 (FC) | 90 |
| 19 | GLM-4.6 (FC thinking) | 89.5 |
| 19 | Gemini-2.5-Flash-Lite (Prompt) | 89.5 |
| 19 | Gemma-3-27b-it (Prompt) | 89.5 |
| 19 | Qwen3-4B-Instruct-2507 (Prompt) | 89.5 |
| 19 | Qwen3-8B (Prompt) | 89.5 |
| 19 | palmyra-x-004 (FC) | 89.5 |
| 19 | xLAM-2-70b-fc-r (FC) | 89.5 |
| 26 | Arch-Agent-32B | 89 |
| 26 | Falcon3-7B-Instruct (FC) | 89 |
| 26 | GPT-4.1-2025-04-14 (Prompt) | 89 |
| 26 | Qwen3-8B (FC) | 89 |
| 30 | Claude-Haiku-4-5-20251001 (FC) | 88.5 |
| 30 | Claude-Opus-4-5-20251101 (FC) | 88.5 |
| 30 | CoALM-8B | 88.5 |
| 30 | Command A Reasoning (FC) | 88.5 |
| 30 | Llama-4-Maverick-17B-128E-Instruct-FP8 (FC) | 88.5 |
| 30 | Qwen3-30B-A3B-Instruct-2507 (FC) | 88.5 |
| 36 | Command A (FC) | 88 |
| 36 | Qwen3-30B-A3B-Instruct-2507 (Prompt) | 88 |
| 38 | Falcon3-10B-Instruct (FC) | 87.5 |
| 38 | Gemini-2.5-Flash (Prompt) | 87.5 |
| 40 | Grok-4-0709 (FC) | 87 |
| 41 | DeepSeek-V3.2-Exp (Prompt + Thinking) | 86.5 |
| 42 | Amazon-Nova-2-Lite-v1:0 (FC) | 86 |
| 42 | Hammer2.1-7b (FC) | 86 |
| 44 | Mistral-Medium-2505 | 85.5 |
| 45 | Nanbeige4-3B-Thinking-2511 (FC) | 84.5 |
| 45 | Open-Mistral-Nemo-2407 (FC) | 84.5 |
| 47 | Amazon-Nova-Pro-v1:0 (FC) | 84 |
| 48 | GPT-4.1-mini-2025-04-14 (Prompt) | 83.5 |
| 48 | mistral-large-2411 (FC) | 83.5 |
| 48 | xLAM-2-8b-fc-r (FC) | 83.5 |