Rankings / Google DeepMind
Gemini 2.5 Pro Preview 06.05
released 2025-06-05
BenchAtlas Index
as of 2026-07-14
base configuration
rank #137
5 families · 3 categories · medium
Benchmark evidence
10 results
external indices
| ECI | 32K budget | 146.1 points | independent | Epoch AI Benchmarking Hub |
| ECI | 146.1 points | independent | Epoch AI Benchmarking Hub | |
| ECI | 1K budget | 146.1 points | independent | Epoch AI Benchmarking Hub |
factuality
| MASK contamination=Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions. | 55.7 % 51.2–60.2 | independent | Scale Labs |
knowledge science
| GPQA Diamond | 84.8 % | independent | Epoch AI Benchmarking Hub 2025-06-05 | |
| Humanity's Last Exam contamination=Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. · implementation=scale | 21.6 % 20.0–23.3 | independent | Scale Labs |
multimodal
| VISTA | 54.6 % 54.1–55.2 | independent | Scale Labs |
reasoning math
| EnigmaEval contamination=Potential contamination warning: This model was evaluated after the public release of EnigmaEval, allowing model builder access to the prompts and solutions. | 5.6 % 4.3–6.9 | independent | Scale Labs | |
| FrontierMath | 10.3 % | independent | Epoch AI Benchmarking Hub 2025-07-03 | |
| FrontierMath Tier 4older version | 2.1 % | independent | Epoch AI Benchmarking Hub 2025-07-03 |