Gemini 2.5 Pro Preview (2025-05-06)
Highlights
Top benchmark results for google/gemini-2-5-pro-preview-2025-05-06.
0.77#6
0.83#18
10.62#2
1247#10
0.83#15
0.18#12
1446#3
0.89#3
0.80#6
0.42#12
0.51#3
0.63#10
1.75#3
Benchmark table
| Benchmark | Category | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|
| Aider-Polyglot | code | 0.77 | Whole | Yes | Source |
| AIME 2025 | math | 0.83 | Pass@1 | Yes | Source |
| Confabulations | - | 10.62 | - | No | Source |
| EQ-Bench 3 | - | 1247 | - | No | Source |
| GPQA Diamond | general-knowledge | 0.83 | Pass@1 | Yes | Source |
| Humanity's Last Exam | - | 0.18 | No Tools | Yes | Source |
| LMArena Text | - | 1446 | - | No | Source |
| MMLU | - | 0.89 | Lite | Yes | Source |
| MMMU | - | 0.80 | Pass@1 | Yes | Source |
| NYT Connections | - | 0.42 | - | No | Source |
| SimpleQA | - | 0.51 | - | Yes | Source |
| SWE-Bench | code | 0.63 | - | Yes | Source |
| Thematic Generalisation | - | 1.75 | - | No | Source |
Benchmark comparisons
Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.
SimpleQA
Compare this model with the leading peers for the selected benchmark.
Benchmark
0.51
Rank #3/10
10 models
Showing 10 models around the selected model (out of 10 total).