| Benchmark | Model | Rank | Results |
|---|---|---|---|
| long-context-understanding-on-mrcr-v2-128k | Gemini 3.7 Flash | #1 | Accuracy: 97.0 |
| video-question-answering-on-lvbench | Gemini 3.7 Flash | #3 | Accuracy: 85.4 |
| code-generation-on-terminal-bench-3-0 | Gemini 3.7 Flash (MiniSWE-Agent) | #7 | Accuracy: 14.9 |
| code-generation-on-terminal-bench-2-1 | Gemini 3.7 Flash (Terminus 2) | #9 | Accuracy: 85.8 |
| code-generation-on-deepswe | Gemini 3.7 Flash (High) (MiniSWE-Agent) | #14 | Pass@1: 0.653 |