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

Interactive Decision Making on Textcraft

99.6Success Rate

GPT-4o-1120

Updated 20d ago

Evaluation Results

Method	Links
GPT-4o-1120 2026.05		99.6
Deepseek-V4-Pro 2026.05		99.5
Kimi-K2-Thinking 2026.05		99.2
Deepseek-V4-Pro 2026.05		99.2
Deepseek-V4-Pro 2026.05		98.8
Kimi-K2-Thinking 2026.05		97.6
Kimi-K2-Thinking 2026.05		96.8
GPT-4o-0806 2026.05		96.7
GPT-4o-1120 2026.05		96.7
Minimax-M2.7 2026.05		96.7
MAP-4B 2026.05		95.6
GPT-4o-1120 2026.05		94.7
GPT-4o-0806 2026.05		92.5
Minimax-M2.7 2026.05		92.3
MAP-4B 2026.05		92.3
Minimax-M2.7 2026.05		92.1
GPT-4o-0806 2026.05		91.6
MAP-4B 2026.05		91.2
Qwen3-32B-Thinking 2026.05		90.4
Qwen3-32B-Thinking 2026.05		87.7
Qwen3-8B-Thinking 2026.05		87.1
Qwen3-32B-Thinking 2026.05		82.4
ACT-4B 2026.05		79.4
GPT-4o-mini 2026.05		75.6
ACT-4B 2026.05		74.5
Qwen3-4B-Instruct 2026.05		71.9
ACT-4B 2026.05		70.1
Doubao-Seed-2.0-Pro 2026.05		69.8
Qwen3-8B-Thinking 2026.05		67
Qwen3-30B-A3B-Instruct 2026.05		66.6
Qwen3-8B-Thinking 2026.05		66.4
Doubao-Seed-2.0-Pro 2026.05		65.6
Doubao-Seed-2.0-Pro 2026.05		63.1
Qwen3-4B-Thinking 2026.05		59.6
Qwen3-30B-A3B-Instruct 2026.05		58.6
Qwen3-30B-A3B-Instruct 2026.05		56.8
GPT-4o-mini 2026.05		54.2
GPT-4o-mini 2026.05		46.5
Qwen3-4B-Thinking 2026.05		37.5
Qwen3-4B-Instruct 2026.05		37.1
Qwen3-4B-Thinking 2026.05		35.6
Qwen3-4B-Instruct 2026.05		31.8