Format Variant 21
BFCL · 40 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude-Opus-4-5-20251101 (Prompt) | 86.5 |
| 2 | Claude-Sonnet-4-5-20250929 (Prompt) | 85 |
| 3 | Qwen3-235B-A22B-Instruct-2507 (Prompt) | 84 |
| 4 | Grok-4-0709 (Prompt) | 83.5 |
| 5 | GPT-4.1-2025-04-14 (Prompt) | 82 |
| 5 | Gemini-3-Pro-Preview (Prompt) | 82 |
| 7 | GPT-5.2-2025-12-11 (Prompt) | 80.5 |
| 7 | mistral-large-2411 (Prompt) | 80.5 |
| 9 | Phi-4 (Prompt) | 79.5 |
| 9 | o4-mini-2025-04-16 (Prompt) | 79.5 |
| 11 | Mistral-Medium-2505 | 78 |
| 12 | Qwen3-32B (Prompt) | 77.5 |
| 13 | GPT-5-mini-2025-08-07 (Prompt) | 77 |
| 14 | DeepSeek-V3.2-Exp (Prompt + Thinking) | 76.5 |
| 14 | Gemini-2.5-Flash (Prompt) | 76.5 |
| 14 | Qwen3-4B-Instruct-2507 (Prompt) | 76.5 |
| 17 | o3-2025-04-16 (Prompt) | 75.5 |
| 18 | GPT-5-nano-2025-08-07 (Prompt) | 75 |
| 18 | Qwen3-30B-A3B-Instruct-2507 (Prompt) | 75 |
| 20 | Qwen3-14B (Prompt) | 74.5 |
| 21 | Qwen3-8B (Prompt) | 72 |
| 22 | Gemma-3-27b-it (Prompt) | 71 |
| 23 | Gemini-2.5-Flash-Lite (Prompt) | 68.5 |
| 24 | Open-Mistral-Nemo-2407 (Prompt) | 68 |
| 25 | Mistral-Small-2506 (Prompt) | 67 |
| 26 | GPT-4.1-nano-2025-04-14 (Prompt) | 65 |
| 27 | GPT-4.1-mini-2025-04-14 (Prompt) | 52 |
| 28 | Bielik-11B-v2.3-Instruct (Prompt) | 50 |
| 28 | MiniCPM3-4B (Prompt) | 50 |
| 30 | Gemma-3-12b-it (Prompt) | 35.5 |
| 31 | Claude-Haiku-4-5-20251001 (Prompt) | 30 |
| 32 | ToolACE-2-8B (FC) | 9 |
| 33 | Gemma-3-4b-it (Prompt) | 8 |
| 34 | Llama-3.1-8B-Instruct (Prompt) | 7 |
| 35 | CoALM-70B | 0 |
| 35 | CoALM-8B | 0 |
| 35 | Gemma-3-1b-it (Prompt) | 0 |
| 35 | Ministral-8B-Instruct-2410 (FC) | 0 |
| 35 | Qwen3-0.6B (Prompt) | 0 |
| 35 | RZN-T (Prompt) | 0 |