Benchmark Registry

IFEval

IFEval results reported for 5 models across 1 version. Updated 2026-09-24.

Report an issue

Versions

1 version · Metric: Accuracy

VersionReleasedModelsResults
IFEval OriginalLatestNovember 14, 202355

Recently reported results: IFEval Original

Latest version: IFEval Original

ModelScoreSource
Gemma 4 31B Instruct (thinking mode)98.9%huggingface.coAccuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord
Gemma 4 26B A4B Instruct (thinking mode)98.5%huggingface.coAccuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord
Gemma 4 12B Instruct (thinking mode)97.2%huggingface.coAccuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord
Gemma 4 E2B Instruct (thinking mode)94.6%huggingface.coAccuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord
Gemma 4 E4B Instruct (thinking mode)96.7%huggingface.coAccuracyReported Model cardGoogleSelf-reportedGoogle DeepMindRecord