Benchmarks

7 results across 7 benchmarks

Benchmark results for Phi-4 Reasoning Vision 15B
BenchmarkScoreSource
AI2D TESTReported as: automatic think/nothink84.8%huggingface.co for Phi-4 Reasoning Vision 15B (automatic think/nothink) on AI2D TEST (opens in a new tab)AccuracyReported Model cardMicrosoftSelf-reportedRecord for Phi-4 Reasoning Vision 15B on AI2D TEST
ChartQA TESTReported as: automatic think/nothink83.3%huggingface.co for Phi-4 Reasoning Vision 15B (automatic think/nothink) on ChartQA TEST (opens in a new tab)AccuracyReported Model cardMicrosoftSelf-reportedRecord for Phi-4 Reasoning Vision 15B on ChartQA TEST
HallusionBench OriginalReported as: automatic think/nothink64.4%huggingface.co for Phi-4 Reasoning Vision 15B (automatic think/nothink) on HallusionBench Original (opens in a new tab)AccuracyReported Model cardMicrosoftSelf-reportedRecord for Phi-4 Reasoning Vision 15B on HallusionBench Original
MathVerse MINIReported as: automatic think/nothink44.9%huggingface.co for Phi-4 Reasoning Vision 15B (automatic think/nothink) on MathVerse MINI (opens in a new tab)AccuracyReported Model cardMicrosoftSelf-reportedRecord for Phi-4 Reasoning Vision 15B on MathVerse MINI
MathVista MINIReported as: automatic think/nothink75.2%huggingface.co for Phi-4 Reasoning Vision 15B (automatic think/nothink) on MathVista MINI (opens in a new tab)AccuracyReported Model cardMicrosoftSelf-reportedRecord for Phi-4 Reasoning Vision 15B on MathVista MINI
MMStar OriginalReported as: automatic think/nothink64.5%huggingface.co for Phi-4 Reasoning Vision 15B (automatic think/nothink) on MMStar Original (opens in a new tab)AccuracyReported Model cardMicrosoftSelf-reportedRecord for Phi-4 Reasoning Vision 15B on MMStar Original
OCRBench OriginalReported as: automatic think/nothink76.0%huggingface.co for Phi-4 Reasoning Vision 15B (automatic think/nothink) on OCRBench Original (opens in a new tab)AccuracyReported Model cardMicrosoftSelf-reportedRecord for Phi-4 Reasoning Vision 15B on OCRBench Original