Results

5 results

BIG-Bench Extra Hard Original — micro average results
ProviderModelScoreSourceRegistry No.
Google (DeepMind)Gemma 4 26B A4B Instruct (thinking mode)64.8%huggingface.co for Gemma 4 26B A4B Instruct (thinking mode) on BIG-Bench Extra Hard Original — micro average (opens in a new tab)Micro-average accuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord for Gemma 4 26B A4B Instruct on BIG-Bench Extra Hard Original — micro average35001
Google (DeepMind)Gemma 4 31B Instruct (thinking mode)74.4%huggingface.co for Gemma 4 31B Instruct (thinking mode) on BIG-Bench Extra Hard Original — micro average (opens in a new tab)Micro-average accuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord for Gemma 4 31B Instruct on BIG-Bench Extra Hard Original — micro average35002
Google (DeepMind)Gemma 4 E2B Instruct (thinking mode)21.9%huggingface.co for Gemma 4 E2B Instruct (thinking mode) on BIG-Bench Extra Hard Original — micro average (opens in a new tab)Micro-average accuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord for Gemma 4 E2B Instruct on BIG-Bench Extra Hard Original — micro average35003
Google (DeepMind)Gemma 4 E4B Instruct (thinking mode)33.1%huggingface.co for Gemma 4 E4B Instruct (thinking mode) on BIG-Bench Extra Hard Original — micro average (opens in a new tab)Micro-average accuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord for Gemma 4 E4B Instruct on BIG-Bench Extra Hard Original — micro average35004
Google (DeepMind)Gemma 4 12B Instruct (thinking mode)53.0%huggingface.co for Gemma 4 12B Instruct (thinking mode) on BIG-Bench Extra Hard Original — micro average (opens in a new tab)Micro-average accuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord for Gemma 4 12B Instruct on BIG-Bench Extra Hard Original — micro average35005