List your company
ResearchFormerly WizWand

Instruction Following on IFEval (IFScore)

84.63IFScoreGemini2.5-Flash
33.867647.046360.22573.4037Sep 9, 2025Oct 20, 2025Nov 30, 2025Jan 10, 2026Feb 20, 2026Apr 2, 2026May 14, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Gemini2.5-FlashModel Category=Proprietary Audio Language Models2025.0984.63
Qwen3-Omni-30B-A3B-ThinkingModel Category=Large Sized Large Audio Language Models, Parameter Count=>20B parameters2025.0980.39
Whisper-Large-v3 + GPT-oSS-20BModel Category=Cascaded Systems2025.0973.72
GPT-4o-mini-audioModel Category=Proprietary Audio Language Models2025.0970.47
Voxtral-Small-24BModel Category=Large Sized Large Audio Language Models, Parameter Count=>20B parameters2025.0966.83
GPT-4o-transcribe + GPT-4.1-miniModel Category=Cascaded Systems2025.0966.69
Kimi-AudioModel Category=Medium Sized Large Audio Language Models, Parameter Count=5B-20B parameters2025.0961.29
Zero-shotBackbone=Llama-3.1-8B-Instruct2026.0556
MANSUBackbone=Llama-3.1-8B-Instruct, Unlearning Task=WMDP-bio2026.0555.1
MANSUBackbone=Llama-3.1-8B-Instruct, Unlearning Task=WMDP-chem2026.0554.9
MANSUBackbone=Llama-3.1-8B-Instruct, Unlearning Task=WMDP-cyber2026.0554.9
Zero-shotBackbone=Qwen-3-8B2026.0554.8
MANSUBackbone=Llama-3.1-8B-Instruct, Unlearning Task=MUSE2026.0554.7
MANSUBackbone=Qwen-3-8B, Unlearning Task=WMDP-cyber2026.0554.2
MANSUBackbone=Qwen-3-8B, Unlearning Task=WMDP-bio2026.0554.1
MANSUBackbone=Qwen-3-8B, Unlearning Task=WMDP-chem2026.0553.9
Qwen2.5-Omni-7BModel Category=Medium Sized Large Audio Language Models, Parameter Count=5B-20B parameters2025.0950.83
Phi-4-Multi-modalModel Category=Medium Sized Large Audio Language Models, Parameter Count=5B-20B parameters2025.0944.51
MANSUBackbone=Qwen-3-8B, Unlearning Task=MUSE2026.0543.6
Voxtral-Mini-3BModel Category=Small-sized Audio Language Models, Parameter Count=<5B parameters2025.0940.02
Qwen2.5-Omni-3BModel Category=Small-sized Audio Language Models, Parameter Count=<5B parameters2025.0935.82