Gemini 2.5 Flash Lite Preview
Highlights
Top benchmark results for google/gemini-2-5-flash-lite-preview-2025-06-17.
0.27#29
0.63#26
0.67#40
0.07#19
1387#16
0.73#11
0.13#9
0.45#17
Benchmark table
| Benchmark | Category | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|
| Aider-Polyglot | code | 0.27 | Thinking | Yes | Source |
| AIME 2025 | math | 0.63 | Thinking | Yes | Source |
| GPQA Diamond | general-knowledge | 0.67 | Thinking | Yes | Source |
| Humanity's Last Exam | - | 0.07 | Thinking, No Tools | Yes | Source |
| LMArena Text | - | 1387 | Thinking | No | Source |
| MMMU | - | 0.73 | Thinking | Yes | Source |
| SimpleQA | - | 0.13 | Thinking | Yes | Source |
| SWE-Bench | code | 0.45 | Thinking, Multiple Attempts | Yes | Source |
Benchmark comparisons
Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.
MMMU
Compare this model with the leading peers for the selected benchmark.
Benchmark
0.73
Rank #11/15
15 models
Lower is better
Lower scores indicate stronger performance.
Showing 11 models around the selected model (out of 15 total).