Gemini 1.0 Ultra: benchmark results
Provider: Google. Released 2023-12-06. Access: API.
Aggregate Rating 1521 ± 51, rank #2053 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CodeEditorBench Plus - Code Debug (Three-shot) | 28.6 | pass@1 (%, greedy decoding, three-shot, CodeEditorBench_Plus | 94.4 |
| CodeEditorBench Plus - Code Debug (Zero-shot) | 30.4 | pass@1 (%, greedy decoding, zero-shot, CodeEditorBench_Plus) | 94.4 |
| CodeEditorBench Plus - Code Translate (Three-shot) | 44.3 | pass@1 (%, greedy decoding, three-shot, CodeEditorBench_Plus | 94.4 |
| CodeEditorBench Plus - Code Translate (Zero-shot) | 37.8 | pass@1 (%, greedy decoding, zero-shot, CodeEditorBench_Plus) | 77.8 |
| DROP | 82.4 | F1 Score | 66.7 |
| MMMU Benchmark | 59.4 | Validation Score | 61.7 |
| CodeEditorBench Plus - Code Requirement Switch (Three-shot) | 15.2 | pass@1 (%, greedy decoding, three-shot, CodeEditorBench_Plus | 61.1 |
| CodeEditorBench Plus - Code Requirement Switch (Zero-shot) | 4.1 | pass@1 (%, greedy decoding, zero-shot, CodeEditorBench_Plus) | 33.3 |
Interactive version: theaggregate.ai/model?slug=gemini-1-0-ultra · How It Works · Data refreshed daily, snapshot 2026-11-08.