Exact model identity
gemini-3.1-pro-preview
Google · version status: reported
Similar model names are never merged automatically. Evaluation membership and numeric result rows only reference the exact ID
gemini-3-1-pro-preview.Evaluation settings
| Benchmark | Work | Run / group | Scope |
|---|---|---|---|
| BioSecBench-Surveillance | BioSecBench-Surveillance repository result snapshot | biosecbench-8d53fd8-pi biosecbench-8d53fd8-pi | full · n=100 |
| SpatialBench | SpatialBench 159-evaluation repository snapshot | spatialbench-repo-159-mini-swe-agent spatialbench-repo-159-mini-swe-agent | full · n=159 |
Numeric results
| Benchmark | Work | Run / group | Metric | Value |
|---|---|---|---|---|
| BioSecBench-Surveillance | BioSecBench-Surveillance repository result snapshot | biosecbench-8d53fd8-pi biosecbench-8d53fd8-pi | endpoint pass rate | 45.3 % |
| SpatialBench | SpatialBench 159-evaluation repository snapshot | spatialbench-repo-159-mini-swe-agent spatialbench-repo-159-mini-swe-agent | Accuracy | 51.57 percent |
| SpatialBench | SpatialBench 159-evaluation repository snapshot | spatialbench-repo-159-mini-swe-agent spatialbench-repo-159-mini-swe-agent | Cost | 0.9362 USD per evaluation |
| SpatialBench | SpatialBench 159-evaluation repository snapshot | spatialbench-repo-159-mini-swe-agent spatialbench-repo-159-mini-swe-agent | Duration | 1061.63 seconds per evaluation |