Share your thoughts, 1 month free Claude Pro on usSee more

Flowchart-Oriented Dialogue on FLODIAL Overall 1.0

81.38INGA

GPT-5

Updated 1mo ago

Evaluation Results

Method	Links
GPT-5 2026.02		81.38	87.16	79.29	0.62	1.15
GPT-5 2026.02		81.38	87.16	79.29	0.62	1.15
GPT-5 2026.02		77.85	50.1	29.39	9.1	8.45
SA-FloNet 2026.02		67.75	1.65	0.2	0	23.24
GPT-4o 2026.02		62.11	91.71	90.88	0	0.15
Llama-3.3-70B 2026.02		61.77	83.85	83.01	0	0.86
GPT-5 2026.02		61.45	91.92	90.88	0	0.6
Claude Opus 4.1 2026.02		61.02	91.3	90.46	0	0.23
Claude Opus 4.1 2026.02		60.85	83.43	80.12	0	0.38
Claude Opus 4.1 2026.02		60.62	87.16	6.62	0	42.25
Deepseek-R1 2026.02		60.44	90.26	89.84	0	0.45
Qwen3 2026.02		59.9	91.71	90.88	0	0.64
GPT-4o 2026.02		54.85	33.12	12.83	0.62	2.6
Deepseek-R1 2026.02		54.31	76.81	66.66	1.03	1.1
GPT-4o 2026.02		52.87	78.26	73.49	0	0.85
Deepseek-R1 2026.02		52.69	76.81	66.66	0	1.39
Llama-3.3-70B 2026.02		52.32	0	0	82.81	55.11
GPT-4o 2026.02		51.29	80.53	75.98	0	0.72
Llama-3.3-70B 2026.02		50	0.2	0	86.12	69.54
Claude Opus 4.1 2026.02		49.2	16.35	3.72	0.2	1.8
Qwen3 2026.02		49.13	71.84	51.12	4.14	5.94
Qwen3 2026.02		40.11	67.7	54.24	0.41	4.34
Qwen-VL-Max 2026.02		38.55	36.23	12.62	4.34	5.18