Gemini 1.0 Pro (001): benchmark results
Google's Gemini 1.0 Pro (001), a text-focused model for multi-turn chat and code generation, from Google's first Gemini generation (released February 2024). Provider: Google. Released 2024-02-01. Access: API.
Aggregate Rating 1392 ± 10, rank #1503 of 2163 rated models, from 63 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM MMLU - Computer Security | 84 | EM | 78.2 |
| HELM MMLU - College Mathematics | 51 | EM | 66.7 |
| HELM MMLU - Jurisprudence | 86.11 | EM | 57.1 |
| MMLU | 70 | Accuracy (%) | 57.1 |
| HELM MMLU - Sociology | 90.05 | EM | 55.1 |
| HELM MMLU - Security Studies | 80.41 | EM | 50 |
| HELM MMLU - International Law | 87.6 | EM | 47.4 |
| HELM MMLU - World Religions | 85.96 | EM | 47.4 |
| HELM MMLU - Global Facts | 49 | EM | 46.2 |
| HELM MMLU - Human Aging | 77.58 | EM | 44.2 |
| HELM MMLU - High School Computer Science | 79 | EM | 42.9 |
| HELM MMLU - High School Biology | 86.13 | EM | 40.4 |
Interactive version: theaggregate.ai/model?slug=gemini-1-0-pro-001 · How It Works · Data refreshed daily, snapshot 2026-10-24.