Gemini 1.5 Pro (001): benchmark results
Gemini 1.5 Pro 001 stable API snapshot. Provider: Google. Released 2024-05-23. Access: API.
Aggregate Rating 1599 ± 14, rank #444 of 1656 rated models, from 237 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Big-Bench Hard | 89.2 | Average (%) | 100 |
| HELM Lite - LegalBench | 75.72 | Exact Match (%) | 100 |
| HELM MMLU - Conceptual Physics | 94.89 | EM | 100 |
| LogicKor - Math | 9.28 | Score (0-10) | 99.6 |
| LogicKor - Single-Turn | 9.4 | Score (0-10) | 99.6 |
| HELM MMLU - High School Geography | 95.96 | EM | 99.4 |
| HELM Lite - LegalBench - Corporate Lobbying | 86.12 | Exact Match (%) | 98.9 |
| HELM Lite - LegalBench - PROA | 100 | Exact Match (%) | 98.9 |
| LogicKor | 9.29 | Score (0-10) | 98.9 |
| LogicKor - Grammar | 9.21 | Score (0-10) | 98.9 |
| HELM MMLU - College Mathematics | 79 | EM | 98.7 |
| Thai LLM - Reasoning | 7.95 | Rating (0-10) | 98.6 |
Interactive version: theaggregate.ai/model?slug=gemini-1-5-pro-001 · How It Works · Data refreshed daily, snapshot 2026-10-20.