Format Variant 9
BFCL · 40 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude-Sonnet-4-5-20250929 (Prompt) | 86.5 |
| 2 | Claude-Opus-4-5-20251101 (Prompt) | 86 |
| 3 | Gemini-3-Pro-Preview (Prompt) | 83 |
| 3 | mistral-large-2411 (Prompt) | 83 |
| 5 | Qwen3-14B (Prompt) | 82.5 |
| 6 | Grok-4-0709 (Prompt) | 82 |
| 7 | GPT-4.1-2025-04-14 (Prompt) | 81.5 |
| 7 | GPT-5.2-2025-12-11 (Prompt) | 81.5 |
| 7 | Qwen3-4B-Instruct-2507 (Prompt) | 81.5 |
| 10 | DeepSeek-V3.2-Exp (Prompt + Thinking) | 80.5 |
| 10 | Qwen3-32B (Prompt) | 80.5 |
| 10 | Qwen3-8B (Prompt) | 80.5 |
| 13 | Gemini-2.5-Flash (Prompt) | 80 |
| 13 | Mistral-Medium-2505 | 80 |
| 15 | Open-Mistral-Nemo-2407 (Prompt) | 79.5 |
| 16 | Qwen3-235B-A22B-Instruct-2507 (Prompt) | 78.5 |
| 16 | o4-mini-2025-04-16 (Prompt) | 78.5 |
| 18 | GPT-4.1-mini-2025-04-14 (Prompt) | 77 |
| 19 | GPT-5-mini-2025-08-07 (Prompt) | 76 |
| 19 | GPT-5-nano-2025-08-07 (Prompt) | 76 |
| 19 | Qwen3-30B-A3B-Instruct-2507 (Prompt) | 76 |
| 22 | o3-2025-04-16 (Prompt) | 73.5 |
| 23 | Mistral-Small-2506 (Prompt) | 69.5 |
| 24 | Bielik-11B-v2.3-Instruct (Prompt) | 67 |
| 25 | Gemini-2.5-Flash-Lite (Prompt) | 65 |
| 26 | Claude-Haiku-4-5-20251001 (Prompt) | 63 |
| 27 | Gemma-3-27b-it (Prompt) | 50.5 |
| 28 | CoALM-70B | 34 |
| 29 | Gemma-3-12b-it (Prompt) | 33 |
| 30 | Phi-4 (Prompt) | 11 |
| 31 | GPT-4.1-nano-2025-04-14 (Prompt) | 10 |
| 32 | Gemma-3-4b-it (Prompt) | 9.5 |
| 33 | Llama-3.1-8B-Instruct (Prompt) | 7 |
| 34 | MiniCPM3-4B (Prompt) | 3 |
| 34 | Qwen3-0.6B (Prompt) | 3 |
| 36 | RZN-T (Prompt) | 1.5 |
| 37 | CoALM-8B | 0 |
| 37 | Gemma-3-1b-it (Prompt) | 0 |
| 37 | Ministral-8B-Instruct-2410 (FC) | 0 |
| 37 | ToolACE-2-8B (FC) | 0 |