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

Flowchart-Oriented Dialogue on FLODIAL 1.0 (Root-init)

100INGA

Llama-3.3-70B

Updated 1mo ago

Evaluation Results

Method	Links
Llama-3.3-70B 2026.02		100
Deepseek-R1 2026.02		100
Claude Opus 4.1 2026.02		98.85
GPT-4o 2026.02		98.85
GPT-4o 2026.02		98.85
Claude Opus 4.1 2026.02		98.57
GPT-4o 2026.02		98.28
GPT-5 2026.02		98.28
Llama-3.3-70B 2026.02		97.42
Claude Opus 4.1 2026.02		97.42
Qwen3 2026.02		97.42
GPT-5 2026.02		94.85
GPT-5 2026.02		94.85
SA-FloNet 2026.02		93.71
Deepseek-R1 2026.02		93.71
Deepseek-R1 2026.02		89.71
Qwen3 2026.02		88.57
Llama-3.3-70B 2026.02		86
Claude Opus 4.1 2026.02		85.71
GPT-5 2026.02		82.57
Qwen3 2026.02		78
Qwen-VL-Max 2026.02		71.14
GPT-4o 2026.02		59.71