Reference
Compare models
Select models and benchmarks. Scores are shown exactly within each benchmark’s own metric — never combined into an aggregate, average, or winner.
Models
1 selected
Grok 4xAI
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | Grok 4xAI |
|---|---|
| SWE-bench Verified% resolved | — |
| GPQA Diamondaccuracy | 87.0% |
SWE-bench Verified
% resolved
Grok 4 · xAI
—
GPQA Diamond
accuracy
Grok 4 · xAI
87.0%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.