← BFCL leaderboards

Memory KV

BFCL · 50 models

RankModelScore
1Claude-Opus-4-5-20251101 (FC)70.97
2Gemini-3-Pro-Preview (Prompt)59.35
3Grok-4-0709 (FC)57.42
4Claude-Sonnet-4-5-20250929 (FC)54.19
5Claude-Haiku-4-5-20251001 (FC)51.61
6Gemini-3-Pro-Preview (FC)50.32
7DeepSeek-V3.2-Exp (Prompt + Thinking)46.45
8GLM-4.6 (FC thinking)43.87
8Grok-4-0709 (Prompt)43.87
10DeepSeek-V3.2-Exp (FC)41.94
11Grok-4-1-fast-reasoning (FC)41.29
12Nanbeige3.5-Pro-Thinking (FC)38.06
13GPT-5-mini-2025-08-07 (FC)36.77
14GPT-5.2-2025-12-11 (FC)33.55
14o3-2025-04-16 (Prompt)33.55
16Nanbeige4-3B-Thinking-2511 (FC)31.61
17o3-2025-04-16 (FC)24.52
18GPT-4.1-mini-2025-04-14 (FC)22.58
18o4-mini-2025-04-16 (Prompt)22.58
20Moonshotai-Kimi-K2-Instruct (FC)21.94
21GPT-4.1-mini-2025-04-14 (Prompt)20.65
21GPT-5-nano-2025-08-07 (Prompt)20.65
21Grok-4-1-fast-non-reasoning (FC)20.65
24GPT-5-mini-2025-08-07 (Prompt)19.35
24Gemini-2.5-Flash (FC)19.35
24o4-mini-2025-04-16 (FC)19.35
27mistral-large-2411 (FC)18.71
28GPT-5-nano-2025-08-07 (FC)18.06
29Phi-4 (Prompt)17.42
30mistral-large-2411 (Prompt)16.77
31Command A Reasoning (FC)16.13
31GPT-4.1-2025-04-14 (FC)16.13
31Mistral-Medium-250516.13
31Qwen3-4B-Instruct-2507 (FC)16.13
35Mistral-Medium-2505 (FC)15.48
36Gemini-2.5-Flash (Prompt)13.55
36Qwen3-32B (Prompt)13.55
38Qwen3-235B-A22B-Instruct-2507 (Prompt)12.9
38Qwen3-4B-Instruct-2507 (Prompt)12.9
40Falcon3-10B-Instruct (FC)12.26
40Qwen3-32B (FC)12.26
42Falcon3-7B-Instruct (FC)10.32
42GPT-4.1-nano-2025-04-14 (FC)10.32
44GPT-4.1-2025-04-14 (Prompt)9.68
44Gemma-3-4b-it (Prompt)9.68
44Granite-3.1-8B-Instruct (FC)9.68
44MiniCPM3-4B-FC (FC)9.68
44Open-Mistral-Nemo-2407 (Prompt)9.68
49CoALM-70B9.03
49GPT-4.1-nano-2025-04-14 (Prompt)9.03