Gemini 2.5 Flash Preview (2025-05-20)
Highlights
Top benchmark results for google/gemini-2-5-flash-preview-2025-05-20.
0.62#10
0.72#21
0.83#14
0.11#15
1417#6
1305#6
0.88#5
0.80#5
0.27#10
0.60#13
Benchmark table
Detailed scores across tracked benchmarks.
| Benchmark | Category | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|
| Aider-Polyglot | code | 0.62 | Whole | Yes | Source |
| AIME 2025 | math | 0.72 | Pass@1 | Yes | Source |
| GPQA Diamond | general-knowledge | 0.83 | Pass@1 | Yes | Source |
| Humanity's Last Exam | - | 0.11 | No Tools | Yes | Source |
| LMArena Text | - | 1417 | - | No | Source |
| LMArena WebDev | - | 1305 | 16th June 2025 | No | Source |
| MMLU | - | 0.88 | Lite | Yes | Source |
| MMMU | - | 0.80 | Pass@1 | Yes | Source |
| SimpleQA | - | 0.27 | - | Yes | Source |
| SWE-Bench | code | 0.60 | - | Yes | Source |
Benchmark comparisons
Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.
GPQA Diamond
Compare this model with the leading peers for the selected benchmark.
Benchmark
0.83
Rank #14/107
107 models
Showing 11 models around the selected model (out of 107 total).