Loading data...
Gemma 4 E2B: benchmark results
Google DeepMind's Gemma 4 E2B, a multimodal (text, image, audio) model in the five-size Gemma 4 family, with a 256K-token context, support for 140+ languages and configurable reasoning modes. Provider: Google. Released 2026-04-02. Access: Open.
Aggregate Rating 1434 ± 12, rank #4541 of 10318 rated models, from 548 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
| Jais 3 Model Cards - SimpleQA Verified (Arabic) - Non-hallucination Rate | 84.8 | Non-hallucination rate (%) | 100 |
| Lara Mini Base Report (base-model long-context protocol) - HELMET 128k | 58.6 | Mean of four HELMET categories (recall, RAG, re-ranking, in- | 100 |
| Lara Mini Base Report (base-model long-context protocol) - HELMET 32k | 66 | Mean of four HELMET categories (recall, RAG, re-ranking, in- | 100 |
| Lara Mini Base Report (base-model long-context protocol) - ONERULER 128k | 84.7 | Mean of four ONERULER retrieval tasks in 26 languages (answe | 100 |
| Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot) | 62.2 | Accuracy (%) averaged over all languages/variants of the ben | 96.3 |
| Lara Mini Base Report (base-model protocol) - Global PIQA (parallel), All Languages (0-shot) | 28.3 | Accuracy (%) averaged over all languages/variants of the ben | 96.3 |
| Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot) | 49.8 | Accuracy normalized by answer length (%) averaged over all l | 96.3 |
| Lara Mini Base Report (base-model protocol) - XCOPA, All Languages (0-shot) | 64.1 | Accuracy (%) averaged over all languages/variants of the ben | 95.4 |
| POLAR-Bench - Utility | 87.56 | Utility score (%): share of the task-relevant attributes the | 95.2 |
| QIMMA - ArabLegalQA | 72.39 | BERTScore F1 (%) | 93.2 |
| AA-Omniscience Hallucination Rate | 32.36 | Hallucination Rate (%) | 90.6 |
| Lara Mini Base Report (base-model protocol) - XNLI, All Languages (0-shot) | 43.5 | Accuracy (%) averaged over all languages/variants of the ben | 89.8 |
Interactive version: theaggregate.ai/model?slug=gemma-4-e2b · How It Works · Data refreshed daily, snapshot 2026-11-14.