Gemini 2.5 Pro
Google·
LLMsflagshipcloud
Overview
Thinking model with enhanced reasoning capabilities.
Capabilities and innovations
Thinking/reasoningCode generationMultimodalThinking ModeEnhanced ReasoningExperimental Preview
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 80.3% | unsourced |
| Humanity’s Last Exam (no tools) | 24.5% | unsourced |
| SWE-bench Verified | 55.4% | unsourced |
| MMLU | 89.5% | unsourced |
| MMLU-Pro | 84.06% | unsourced |
- SWE-bench Pro: benchmark did not exist at release
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Links
More from Google
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.