List your company

Complex Reasoning and Instruction Following on ItaBench leaderboard tasks

37.88BBH-it ScoreQwen2.5
29.66431.79733.9336.063Dec 25, 2025

Evaluation results

MethodLinks
Qwen2.52025.1237.8826.9137.9628.6923.39
Gamayun2025.1236.7430.1136.7737.4821.03
Qwen32025.1236.6127.5940.3424.2226.13
Llama3.22025.1233.2426.5836.7728.9817.48
Gemma32025.1231.6126.6635.4541.7313.2
EuroLM2025.1229.9824.7337.9626.1810.26