Exact model identity
Grok-4.1 (SpatialBench paper label)
xAI · version status: not reported
Similar model names are never merged automatically. Evaluation membership and numeric result rows only reference the exact ID
spatialbench-grok-4-1-unversioned.Evaluation settings
| Benchmark | Work | Run / group | Scope |
|---|---|---|---|
| SpatialBench | SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? | spatialbench-paper-v2-base spatialbench-paper-v2-base | full · n=146 |
Numeric results
| Benchmark | Work | Run / group | Metric | Value |
|---|---|---|---|---|
| SpatialBench | SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? | spatialbench-paper-v2-base spatialbench-paper-v2-base | Accuracy | 24.66 percent |
| SpatialBench | SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? | spatialbench-paper-v2-base spatialbench-paper-v2-base | Steps | 9.93 steps per evaluation |
| SpatialBench | SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? | spatialbench-paper-v2-base spatialbench-paper-v2-base | Latency | 196.4 seconds per evaluation |
| SpatialBench | SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? | spatialbench-paper-v2-base spatialbench-paper-v2-base | Cost | 0.077 USD per evaluation |