List your company

Next-state prediction on TextWorld (TW)

70.6EM AccuracyQwen2.5-7B
-2.82416.23835.354.362Dec 21, 2025

Evaluation results

MethodLinks
Qwen2.5-7BEvaluation Protocol=SFT2025.1270.6
Llama3.1-8BEvaluation Protocol=SFT2025.1270.45
Claude-sonnet-4.5Evaluation Protocol=Few-shot (3 shot)2025.1249.12
GPT-5Evaluation Protocol=Few-shot (3 shot)2025.1244.27
Gemini-2.5-flashEvaluation Protocol=Few-shot (3 shot)2025.1240.35
Claude-sonnet-4.5Evaluation Protocol=Zero-shot2025.1217.7
GPT-4oEvaluation Protocol=Few-shot (3 shot)2025.1214.11
GPT-4.1Evaluation Protocol=Few-shot (3 shot)2025.1213.39
GPT-4-turboEvaluation Protocol=Few-shot (3 shot)2025.1211.66
GPT-4o-miniEvaluation Protocol=Few-shot (3 shot)2025.1211.43
GPT-5Evaluation Protocol=Zero-shot2025.129.2
GPT-4oEvaluation Protocol=Zero-shot2025.127.86
Gemini-2.5-flashEvaluation Protocol=Zero-shot2025.123.51
GPT-4o-miniEvaluation Protocol=Zero-shot2025.120.36
GPT-4-turboEvaluation Protocol=Zero-shot2025.120
GPT-4.1Evaluation Protocol=Zero-shot2025.120