Gemma-4-31B-IT-NVFP4: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1749 ± 34, rank #187 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Horangi 4 - KoBBQ | 98 | Accuracy (%) | 97.1 |
| Horangi 4 - KoBALT-700 (Syntax) | 86 | Accuracy (%) | 94.2 |
| Horangi 4 - KorQuAD 1.0 | 88.24 | F1 (x100) | 94.2 |
| Horangi 4 - KoBALT-700 (Semantics) | 82 | Accuracy (%) | 92.8 |
| Horangi 4 - GLP - Semantic Analysis | 86 | Score (%) | 90.9 |
| Horangi 4 - BFCL | 69.05 | Accuracy (%) | 90 |
| Horangi 4 - SWE-bench Verified (80-task subset) | 58.75 | Resolved (%) | 85.1 |
| Horangi 4 - Ko-HalluLens (Nonexistent Entities) | 90 | Refusal rate (%) | 84.6 |
| Horangi 4 - ALT Average | 78.25 | Score (%) | 83.7 |
| Horangi 4 - KMMLU-Pro | 83 | Accuracy (%) | 82.7 |
| Horangi 4 - Final Score | 76.65 | Score (%) | 81.7 |
| Horangi 4 - IFEval-Ko | 89.58 | Instruction-following accuracy (%) | 81.2 |
Interactive version: theaggregate.ai/model?slug=gemma-4-31b-it-nvfp4 · How It Works · Data refreshed daily, snapshot 2026-11-08.